| Data Scientists: | Myunghwan Lee | Gene Moo Lee |
| Affiliations: | Ph.D. Student of Information Systems University of British Columbia |
Associate Professor of Information Systems University of British Columbia |
| Contact: | myunghwan.lee@sauder.ubc.ca Home Page |
gene.lee@sauder.ubc.ca Home Page |
| Application | Dataset | Task | Sub-task | 2nd-sub-task | Model |
|---|---|---|---|---|---|
| adversarial | multiple | attack | prediction | triad prediction | cgnn |
| adversarial | multiple | attack | prediction | triad prediction | mc-svd |
| adversarial | multiple | attack | attack | adversarial attack | pg |
| adversarial | multiple | attack | attack | adversarial attack | bpda |
| adversarial | multiple | attack | attack | adversarial attack | spsa |
| adversarial | multiple | attack | attack | adversarial attack | cw |
| adversarial | multiple | attack | attack | adversarial attack | elastic net |
| adversarial | multiple | attack | attack | adversarial attack | fgsm |
| adversarial | multiple | attack | attack | real-word adversarial attack | advhat |
| adversarial | multiple | attack | attack | real-word adversarial attack | mtcnnattack |
| adversarial | multiple | attack | attack | real-word adversarial attack | adversarial-patch-3d |
| adversarial | multiple | attack | attack | real-word adversarial attack | attack_practical_asv |
| adversarial | multiple | attack | reasoning | inference attack | data_model_dependencies_mia |
| adversarial | multiple | attack | reasoning | inference attack | mi-attack |
| adversarial | multiple | attack | reasoning | inference attack | ml_privacy_meter |
| adversarial | multiple | attack | reasoning | inference attack | privacy-preserving-social-network-embedding |
| adversarial | multiple | attack | reasoning | inference attack | featureinference-vfl |
| adversarial | multiple | attack | reasoning | inference attack | blindmi |
| adversarial | multiple | attack | reasoning | inference attack | gan-leaks |
| adversarial | multiple | attack | reasoning | inference attack | riga |
| adversarial | multiple | attack | reasoning | inference attack | rebmigraph |
| adversarial | multiple | attack | reasoning | inference attack | ml-doctor |
| adversarial | multiple | attack | reasoning | inference attack | adversarial-patch-3d |
| adversarial | multiple | attack | reasoning | inference attack | pricure |
| adversarial | multiple | attack | reasoning | inference attack | security-research-dp-hierarchical-text |
| adversarial | multiple | attack | reasoning | inference attack | membership-inference-attacks-against-object-detection-models |
| adversarial | multiple | attack | reasoning | inference attack | formestdistrisks |
| adversarial | multiple | attack | reasoning | inference attack | aijack |
| adversarial | multiple | attack | reasoning | inference attack | memguard |
| adversarial | multiple | attack | reasoning | inference attack | ecg_gan_mbd |
| adversarial | multiple | attack | reasoning | inference attack | mi-on-el |
| adversarial | multiple | attack | reasoning | inference attack | membershipinferencelottery |
| adversarial | multiple | attack | reasoning | inference attack | soteria |
| adversarial | multiple | attack | reasoning | inference attack | source-inference-fl |
| adversarial | multiple | attack | reasoning | inference attack | mias |
| adversarial | multiple | attack | reasoning | inference attack | mia-gnn |
| adversarial | multiple | attack | reasoning | inference attack | pia_gan |
| adversarial | multiple | attack | reasoning | inference attack | dp-util |
| adversarial | multiple | attack | reasoning | inference attack | fed-ser-leakage |
| adversarial | multiple | attack | reasoning | inference attack | fl-tee |
| adversarial | multiple | attack | reasoning | inference attack | ml-leaks |
| adversarial | multiple | attack | detection | adversarial attack detection | spectraldef_framework |
| adversarial | multiple | attack | detection | adversarial attack detection | featurespaceattack |
| adversarial | multiple | attack | detection | adversarial attack detection | metaadvdet |
| adversarial | multiple | attack | detection | adversarial attack detection | trapdoor |
| adversarial | multiple | attack | detection | adversarial attack detection | sammd |
| adversarial | multiple | attack | attack | website fingerprinting attacks | cnn |
| adversarial | multiple | attack | reasoning | inference attack | mia |
| adversarial | multiple | defense | defense | adversarial defense | stochastic-lwta/pgd/wideresnet-34-10 |
| adversarial | multiple | defense | defense | adversarial defense | sat-efficientnet-l1 |
| adversarial | multiple | defense | defense | adversarial defense | resnet-152 denoise |
| adversarial | multiple | defense | defense | adversarial defense | wideresnet-34-20 |
| adversarial | multiple | defense | defense | adversarial defense | feature denoising |
| adversarial | multiple | defense | defense | adversarial defense | cassandra |
| adversarial | multiple | defense | defense | adversarial defense | auto encoder-block- switching defense with gradcam |
| adversarial | multiple | defense | defense | provable adversarial defense | transformation-smoothing |
| adversarial | multiple | defense | defense | provable adversarial defense | adv-crowd-analysis |
| adversarial | multiple | defense | defense | neural network security | nan |
| adversarial | multiple | defense | defense | website fingerprinting defense | cnn |
| adversarial | multiple | attack | attack | adversarial-attacks-on-face-detectors-using | roi-pooling |
| adversarial | multiple | attack | attack | adversarial-attacks-on-face-detectors-using | convolution |
| adversarial | multiple | attack | attack | adversarial-attacks-on-face-detectors-using | softmax |
| adversarial | multiple | attack | attack | adversarial-attacks-on-face-detectors-using | faster-r-cnn |
| adversarial | multiple | attack | attack | adversarial-attacks-on-face-detectors-using | rpn |
| adversarial | multiple | attack | attack | shapeshifter-robust-physical-adversarial | roi-pooling |
| adversarial | multiple | attack | attack | shapeshifter-robust-physical-adversarial | softmax |
| adversarial | multiple | attack | attack | shapeshifter-robust-physical-adversarial | convolution |
| adversarial | multiple | attack | attack | shapeshifter-robust-physical-adversarial | faster-r-cnn |
| adversarial | multiple | attack | attack | shapeshifter-robust-physical-adversarial | rpn |
| adversarial | multiple | attack | attack | distorting-neural-representations-to-generate | softmax |
| adversarial | multiple | attack | attack | sada-semantic-adversarial-diagnostic-attacks | gan |
| adversarial | multiple | attack | attack | sada-semantic-adversarial-diagnostic-attacks | carla |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | sigmoid-activation |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | squeeze-and-excitation-block |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | roi-align |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | convolution |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | residual-block |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | softmax |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | max-pooling |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | 1x1-convolution |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | resnext |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | relu |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | dense-block |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | he-initialization |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | dropout |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | batch-normalization |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | mask-r-cnn |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | resnet |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | average-pooling |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | dense-connections |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | global-average-pooling |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | senet |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | concatenated-skip-connection |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | densenet |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | resnext-block |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | grouped-convolution |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | residual-connection |
| adversarial | multiple | defense | defense | learning-deep-compositional-grammatical | bottleneck-residual-block |
| computer vision | image, video | classification | video classification | video-classification | dcgn |
| computer vision | image, video | classification | video classification | video-classification | multigrid |
| computer vision | image, video | classification | video classification | video-classification | msnet-r50en |
| computer vision | image, video | classification | video classification | video-classification | mmdl |
| computer vision | image, video | classification | video classification | video-classification | cooperative ours |
| computer vision | image, video | classification | video classification | video-classification | cnn+lstm |
| computer vision | image, video | classification | video classification | group-normalization | roi-align |
| computer vision | image, video | classification | video classification | group-normalization | convolution |
| computer vision | image, video | classification | video classification | group-normalization | softmax |
| computer vision | image, video | classification | video classification | group-normalization | residual-block |
| computer vision | image, video | classification | video classification | group-normalization | max-pooling |
| computer vision | image, video | classification | video classification | group-normalization | focal-loss |
| computer vision | image, video | classification | video classification | group-normalization | group-normalization |
| computer vision | image, video | classification | video classification | group-normalization | 1x1-convolution |
| computer vision | image, video | classification | video classification | group-normalization | relu |
| computer vision | image, video | classification | video classification | group-normalization | retinanet |
| computer vision | image, video | classification | video classification | group-normalization | he-initialization |
| computer vision | image, video | classification | video classification | group-normalization | batch-normalization |
| computer vision | image, video | classification | video classification | group-normalization | mask-r-cnn |
| computer vision | image, video | classification | video classification | group-normalization | fpn |
| computer vision | image, video | classification | video classification | group-normalization | resnet |
| computer vision | image, video | classification | video classification | group-normalization | average-pooling |
| computer vision | image, video | classification | video classification | group-normalization | global-average-pooling |
| computer vision | image, video | classification | video classification | group-normalization | bottleneck-residual-block |
| computer vision | image, video | classification | video classification | group-normalization | residual-connection |
| computer vision | image, video | classification | video classification | non-local-neural-networks | convolution |
| computer vision | image, video | classification | video classification | non-local-neural-networks | residual-block |
| computer vision | image, video | classification | video classification | non-local-neural-networks | max-pooling |
| computer vision | image, video | classification | video classification | non-local-neural-networks | non-local-operation |
| computer vision | image, video | classification | video classification | non-local-neural-networks | embedded-dot-product-affinity |
| computer vision | image, video | classification | video classification | non-local-neural-networks | weight-decay |
| computer vision | image, video | classification | video classification | non-local-neural-networks | 1x1-convolution |
| computer vision | image, video | classification | video classification | non-local-neural-networks | resnext |
| computer vision | image, video | classification | video classification | non-local-neural-networks | relu |
| computer vision | image, video | classification | video classification | non-local-neural-networks | he-initialization |
| computer vision | image, video | classification | video classification | non-local-neural-networks | concatenation-affinity |
| computer vision | image, video | classification | video classification | non-local-neural-networks | batch-normalization |
| computer vision | image, video | classification | video classification | non-local-neural-networks | sgd-with-momentum |
| computer vision | image, video | classification | video classification | non-local-neural-networks | resnet |
| computer vision | image, video | classification | video classification | non-local-neural-networks | embedded-gaussian-affinity |
| computer vision | image, video | classification | video classification | non-local-neural-networks | average-pooling |
| computer vision | image, video | classification | video classification | non-local-neural-networks | global-average-pooling |
| computer vision | image, video | classification | video classification | non-local-neural-networks | resnext-block |
| computer vision | image, video | classification | video classification | non-local-neural-networks | grouped-convolution |
| computer vision | image, video | classification | video classification | non-local-neural-networks | residual-connection |
| computer vision | image, video | classification | video classification | non-local-neural-networks | bottleneck-residual-block |
| computer vision | image, video | classification | video classification | non-local-neural-networks | non-local-block |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | resnet50-v1 |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | inceptionv3 |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | xception |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | opticnet-71 |
| computer vision | image, video | classification | image classification | image-classification | coanet-7 |
| computer vision | image, video | classification | image classification | image-classification | vit-h/14 |
| computer vision | image, video | classification | image classification | image-classification | effnet-l2 |
| computer vision | image, video | classification | image classification | image-classification | wide-resnet-101 |
| computer vision | image, video | classification | image classification | image-classification | cnn+lstm |
| computer vision | image, video | classification | image classification | image-classification | wrn28019 |
| computer vision | image, video | classification | image classification | image-classification | meta pseudo labels |
| computer vision | image, video | classification | image classification | image-classification | cct-14/7*2 |
| computer vision | image, video | classification | image classification | image-classification | mae |
| computer vision | image, video | classification | image classification | image-classification | pgdf |
| computer vision | image, video | classification | image classification | multi-label-image-classification | nan |
| computer vision | image, video | classification | image classification | superpixel-image-classification | nan |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | nan |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | nan |
| computer vision | image, video | classification | image classification | action-classification | mtv-h |
| computer vision | image, video | classification | image classification | action-classification | tokenlearner |
| computer vision | image, video | classification | image classification | action-classification | cover |
| computer vision | image, video | classification | image classification | action-classification | mtv-h |
| computer vision | image, video | classification | image classification | action-classification | tokenlearner |
| computer vision | image, video | classification | image classification | action-classification | vpn++ |
| computer vision | image, video | classification | image classification | action-classification | 3c-net |
| computer vision | image, video | classification | image classification | action-classification | w-talc |
| computer vision | image, video | classification | image classification | action-classification | mars+rgb+flow |
| computer vision | image, video | classification | image classification | scene-classification | isqrt-cov-net |
| computer vision | image, video | classification | image classification | scene-classification | msmatch |
| computer vision | image, video | classification | image segmentation | semantic segmentation | hrnetv2 + ocr |
| computer vision | image, video | classification | image segmentation | semantic segmentation | semask |
| computer vision | image, video | classification | image segmentation | semantic segmentation | swinv2-g |
| computer vision | image, video | segmentation | image segmentation | semantic segmentation | efficientnet-l2+nas-fpn |
| computer vision | image, video | segmentation | image segmentation | semantic segmentation | senformer |
| computer vision | image, video | segmentation | image segmentation | semantic segmentation | hrnetv2-ocr+psa |
| computer vision | image, video | segmentation | image segmentation | semantic segmentation | pointtransformer |
| computer vision | image, video | segmentation | image segmentation | semantic segmentation | mix3d |
| computer vision | image, video | segmentation | image segmentation | semantic segmentation | pointmixer |
| computer vision | image, video | segmentation | image segmentation | real-time-semantic-segmentation | nan |
| computer vision | image, video | segmentation | video segmentation | unsupervised-video-object-segmentation | hcpu |
| computer vision | image, video | segmentation | video segmentation | unsupervised-video-object-segmentation | propose-reduce |
| computer vision | image, video | segmentation | video segmentation | unsupervised-video-object-segmentation | unovsot |
| computer vision | image, video | segmentation | video segmentation | unsupervised-video-object-segmentation | alba |
| computer vision | image, video | segmentation | video segmentation | unsupervised-video-object-segmentation | frameselect |
| computer vision | image, video | segmentation | video segmentation | unsupervised-video-object-segmentation | cosnet |
| computer vision | image, video | segmentation | medical segmentation | medical image segmentation | swin unetr |
| computer vision | image, video | segmentation | medical segmentation | medical image segmentation | nnformer |
| computer vision | image, video | segmentation | medical segmentation | medical image segmentation | unet++ |
| computer vision | image, video | segmentation | medical segmentation | medical image segmentation | dc-unet |
| computer vision | image, video | segmentation | medical segmentation | medical image segmentation | resunet+++tta |
| computer vision | image, video | segmentation | medical segmentation | medical image segmentation | uacanet-l |
| computer vision | image, video | segmentation | medical segmentation | medical image segmentation | msrf-net |
| computer vision | image, video | segmentation | medical segmentation | tumor segmentation | salient attention u-net |
| computer vision | image, video | segmentation | image segmentation | interactive-segmentation | nan |
| computer vision | image, video | segmentation | 3d image segmentation | 3d-instance-segmentation | nan |
| computer vision | image, video | segmentation | image segmentation | hand-segmentation | nan |
| computer vision | image, video | segmentation | video segmentation | video-object-segmentation | nan |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | nan |
| computer vision | image, video | segmentation | video segmentation | video-semantic-segmentation | nan |
| computer vision | image, video | segmentation | image segmentation | human-instance-segmentation | nan |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | nan |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | nan |
| computer vision | image, video | segmentation | image segmentation | one-shot-segmentation | nan |
| computer vision | image, video | segmentation | image caption | image-captioning | nan |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | nan |
| computer vision | image, video | segmentation | one-shot-segmentation | one-shot-segmentation-in-clutter | convolution |
| computer vision | image, video | segmentation | one-shot-segmentation | one-shot-segmentation-in-clutter | max-pooling |
| computer vision | image, video | segmentation | one-shot-segmentation | one-shot-segmentation-in-clutter | relu |
| computer vision | image, video | segmentation | one-shot-segmentation | one-shot-segmentation-in-clutter | u-net |
| computer vision | image, video | segmentation | one-shot-segmentation | one-shot-segmentation-in-clutter | concatenated-skip-connection |
| computer vision | image, video | generation | image generation | image generation | nan |
| computer vision | image, video | generation | image generation | object-proposal-generation | nan |
| computer vision | image, video | generation | image generation | image-augmentation | nan |
| computer vision | image, video | generation | image generation | image-retrieval | nan |
| computer vision | image, video | generation | image generation | image-manipulation | nan |
| computer vision | image, video | generation | video generation | video-retrieval, 3d-shape-retrieval | nan |
| computer vision | image, video | generation | image generation | 3d-reconstruction | roi-pooling |
| computer vision | image, video | generation | image generation | 3d-reconstruction | convolution |
| computer vision | image, video | generation | image generation | 3d-reconstruction | softmax |
| computer vision | image, video | generation | image generation | 3d-reconstruction | faster-r-cnn |
| computer vision | image, video | generation | image generation | 3d-reconstruction | rpn |
| computer vision | image, video | generation | image generation | image-dehazing | nan |
| computer vision | image, video | generation | image generation | image-restoration | nan |
| computer vision | image, video | generation | image generation | image-denoising | nan |
| computer vision | image, video | generation | code prediction | code generation | nan |
| computer vision | image, video | generation | code prediction | code document generation | nan |
| computer vision | image, video | recognition | 3d image recognition | 3d-shape-recognition | nan |
| computer vision | image, video | recognition | image recognition | logo-recognition | triplet-loss |
| computer vision | image, video | recognition | image recognition | person-re-identification | nan |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | nan |
| computer vision | image, video | recognition | image recognition | scene-understanding | nan |
| computer vision | image, video | recognition | image recognition | depth-estimation | nan |
| computer vision | image, video | recognition | image recognition | object-recognition | nan |
| computer vision | image, video | recognition | image recognition | face-recognition, face-verification | nan |
| computer vision | image, video | recognition | image recognition | action-recognition | nan |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | nan |
| computer vision | image, video | recognition | video recognition | video-recognition | nan |
| computer vision | image, video | detection | video detection | video-object detection | nan |
| computer vision | image, video | detection | video detection | video-salient-object-detection | nan |
| computer vision | image, video | detection | image detection | saliency-detection | nan |
| computer vision | image, video | detection | image detection | salient-object-detection | nan |
| computer vision | image, video | detection | image detection | key point detection | nan |
| computer vision | image, video | detection | image detection | fingertip-detection | nan |
| computer vision | image, video | detection | 3d image detection | 3d-object-detection | nan |
| computer vision | image, video | detection | video detection | fish-detection | nan |
| computer vision | image, video | detection | medical detection | medical-object-detection | dkma-uld |
| computer vision | image, video | detection | medical detection | medical-object-detection | attention-based model |
| computer vision | image, video | detection | medical detection | medical-object-detection | wfd-c |
| computer vision | image, video | detection | medical detection | medical-object-detection | circlenet |
| computer vision | image, video | detection | image detection | boundary-detection | convolution |
| computer vision | image, video | detection | image detection | boundary-detection | fcn |
| computer vision | image, video | detection | image detection | boundary-detection | max-pooling |
| computer vision | image, video | detection | image detection | window-detection | nan |
| computer vision | image, video | detection | image detection | scene-text-detection | nan |
| computer vision | image, video | detection | image detection | object-detection | nan |
| computer vision | image, video | detection | image detection | small-object-detection | nan |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | nan |
| computer vision | image, video | detection | image detection | weakly-supervised-object-detection | nan |
| computer vision | image, video | detection | image detection | robust-object-detection | nan |
| computer vision | image, video | detection | image detection | real-time-object-detection | nan |
| computer vision | image, video | detection | image detection | few-shot-object-detection | nan |
| computer vision | image, video | detection | image detection | object-discovery | nan |
| computer vision | image, video | detection | image / video detection | action-detection | nan |
| computer vision | image, video | detection | image / video detection | hand-detection | nan |
| computer vision | image, video | detection | image / video detection | face-detection | nan |
| computer vision | image, video | detection | image / video detection | human-detection | nan |
| computer vision | image, video | detection | image detection | curved-text-detection | nan |
| computer vision | image, video | detection | image detection | defect-detection | nan |
| computer vision | image, video | detection | image-manipulation-detection | image-manipulation-detection | nan |
| computer vision | image, video | detection | image / video detection | fine-grained-action-detection | nan |
| computer vision | image, video | autonomous vehicle | autonomous car detection | visual-object-tracking | nan |
| computer vision | image, video | autonomous vehicle | autonomous car detection | visual-tracking | nan |
| computer vision | image, video | autonomous vehicle | autonomous car detection | object-tracking | nan |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | nan |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-attribute-recognition | nan |
| computer vision | image, video | autonomous vehicle | autonomous car detection | autonomous-navigation | nan |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | dynaslam-tracking-mapping-and-inpainting-in | orb-slam2 |
| computer vision | image, video | autonomous vehicle | autonomous car adversarial | shapeshifter-robust-physical-adversarial | roi-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car adversarial | shapeshifter-robust-physical-adversarial | softmax |
| computer vision | image, video | autonomous vehicle | autonomous car adversarial | shapeshifter-robust-physical-adversarial | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car adversarial | shapeshifter-robust-physical-adversarial | faster-r-cnn |
| computer vision | image, video | autonomous vehicle | autonomous car adversarial | shapeshifter-robust-physical-adversarial | rpn |
| computer vision | image, video | autonomous vehicle | autonomous car generation | joint-3d-proposal-generation-and-object | rpn |
| computer vision | image, video | autonomous vehicle | autonomous car detection | focal-loss-in-3d-object-detection | focal-loss |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | nan |
| computer vision | image, video | conversion | image conversion | cross-view-image-to-image-translation | nan |
| computer vision | image, video | conversion | image conversion | style-transfer | nan |
| computer vision | image, video | classification | image classification | weakly supervised classification | nan |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | resnet |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | rpn |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | average-pooling |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | global-average-pooling |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | roi-pooling |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | faster-r-cnn |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | sniper |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | residual-connection |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | convolution |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | residual-block |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | softmax |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | max-pooling |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | weight-decay |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | 1x1-convolution |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | relu |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | he-initialization |
| computer vision | image, video | detection | object-detection | sniper-efficient-multi-scale-training | batch-normalization |
| computer vision | image, video | detection | object-detection | optimizing-the-trade-off-between-single-stage | mask-r-cnn |
| computer vision | image, video | detection | object-detection | optimizing-the-trade-off-between-single-stage | ssd |
| computer vision | image, video | detection | object-detection | optimizing-the-trade-off-between-single-stage | rpn |
| computer vision | image, video | detection | object-detection | optimizing-the-trade-off-between-single-stage | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | optimizing-the-trade-off-between-single-stage | roi-pooling |
| computer vision | image, video | detection | object-detection | optimizing-the-trade-off-between-single-stage | roi-align |
| computer vision | image, video | detection | object-detection | optimizing-the-trade-off-between-single-stage | convolution |
| computer vision | image, video | detection | object-detection | optimizing-the-trade-off-between-single-stage | softmax |
| computer vision | image, video | detection | object-detection | optimizing-the-trade-off-between-single-stage | faster-r-cnn |
| computer vision | image, video | detection | object-detection | optimizing-the-trade-off-between-single-stage | 1x1-convolution |
| computer vision | image, video | detection | object-detection | dynaslam-tracking-mapping-and-inpainting-in | orb-slam2 |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | global-average-pooling |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | softmax |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | convolution |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | max-pooling |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | 1x1-convolution |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | fire-module |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | relu |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | dropout |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | xavier-initialization |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | residual-connection |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | squeezenet |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | ssd |
| computer vision | image, video | detection | object-detection | fire-ssd-wide-fire-modules-based-single-shot | average-pooling |
| computer vision | image, video | detection | object-detection | group-normalization | roi-align |
| computer vision | image, video | detection | object-detection | group-normalization | convolution |
| computer vision | image, video | detection | object-detection | group-normalization | softmax |
| computer vision | image, video | detection | object-detection | group-normalization | residual-block |
| computer vision | image, video | detection | object-detection | group-normalization | max-pooling |
| computer vision | image, video | detection | object-detection | group-normalization | focal-loss |
| computer vision | image, video | detection | object-detection | group-normalization | group-normalization |
| computer vision | image, video | detection | object-detection | group-normalization | 1x1-convolution |
| computer vision | image, video | detection | object-detection | group-normalization | relu |
| computer vision | image, video | detection | object-detection | group-normalization | retinanet |
| computer vision | image, video | detection | object-detection | group-normalization | he-initialization |
| computer vision | image, video | detection | object-detection | group-normalization | batch-normalization |
| computer vision | image, video | detection | object-detection | group-normalization | mask-r-cnn |
| computer vision | image, video | detection | object-detection | group-normalization | fpn |
| computer vision | image, video | detection | object-detection | group-normalization | resnet |
| computer vision | image, video | detection | object-detection | group-normalization | average-pooling |
| computer vision | image, video | detection | object-detection | group-normalization | global-average-pooling |
| computer vision | image, video | detection | object-detection | group-normalization | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | group-normalization | residual-connection |
| computer vision | image, video | detection | object-detection | patchfcn-for-intracranial-hemorrhage | convolution |
| computer vision | image, video | detection | object-detection | patchfcn-for-intracranial-hemorrhage | fcn |
| computer vision | image, video | detection | object-detection | patchfcn-for-intracranial-hemorrhage | max-pooling |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | yolov2 |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | rpn |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | average-pooling |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | global-average-pooling |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | roi-pooling |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | convolution |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | softmax |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | faster-r-cnn |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | max-pooling |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | darknet-19 |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | 1x1-convolution |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | fast-r-cnn |
| computer vision | image, video | detection | object-detection | model-based-active-learning-to-detect | batch-normalization |
| computer vision | image, video | detection | object-detection | sbnet-sparse-blocks-network-for-fast | convolution |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | rpn |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | dense-connections |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | roi-pooling |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | convolution |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | softmax |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | faster-r-cnn |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | vgg |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | max-pooling |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | relu |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | r-fcn |
| computer vision | image, video | detection | object-detection | quantization-mimic-towards-very-tiny-cnn-for | dropout |
| computer vision | image, video | detection | object-detection | the-eurocity-persons-dataset-a-novel | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | the-eurocity-persons-dataset-a-novel | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | the-eurocity-persons-dataset-a-novel | convolution |
| computer vision | image, video | detection | object-detection | the-eurocity-persons-dataset-a-novel | ssd |
| computer vision | image, video | detection | object-detection | the-eurocity-persons-dataset-a-novel | 1x1-convolution |
| computer vision | image, video | detection | object-detection | the-eurocity-persons-dataset-a-novel | r-fcn |
| computer vision | image, video | detection | object-detection | igcv3-interleaved-low-rank-group-convolutions | average-pooling |
| computer vision | image, video | detection | object-detection | igcv3-interleaved-low-rank-group-convolutions | pointwise-convolution |
| computer vision | image, video | detection | object-detection | igcv3-interleaved-low-rank-group-convolutions | convolution |
| computer vision | image, video | detection | object-detection | igcv3-interleaved-low-rank-group-convolutions | depthwise-separable-convolution |
| computer vision | image, video | detection | object-detection | igcv3-interleaved-low-rank-group-convolutions | mobilenetv2 |
| computer vision | image, video | detection | object-detection | igcv3-interleaved-low-rank-group-convolutions | 1x1-convolution |
| computer vision | image, video | detection | object-detection | igcv3-interleaved-low-rank-group-convolutions | depthwise-convolution |
| computer vision | image, video | detection | object-detection | igcv3-interleaved-low-rank-group-convolutions | inverted-residual-block |
| computer vision | image, video | detection | object-detection | igcv3-interleaved-low-rank-group-convolutions | batch-normalization |
| computer vision | image, video | detection | object-detection | how-convolutional-neural-network-see-the | network-dissection |
| computer vision | image, video | detection | object-detection | adversarial-attacks-on-face-detectors-using | roi-pooling |
| computer vision | image, video | detection | object-detection | adversarial-attacks-on-face-detectors-using | convolution |
| computer vision | image, video | detection | object-detection | adversarial-attacks-on-face-detectors-using | softmax |
| computer vision | image, video | detection | object-detection | adversarial-attacks-on-face-detectors-using | faster-r-cnn |
| computer vision | image, video | detection | object-detection | adversarial-attacks-on-face-detectors-using | rpn |
| computer vision | image, video | detection | object-detection | asynchronous-convolutional-networks-for | max-pooling |
| computer vision | image, video | detection | object-detection | deep-perm-set-net-learn-to-predict-sets-with | roi-pooling |
| computer vision | image, video | detection | object-detection | deep-perm-set-net-learn-to-predict-sets-with | convolution |
| computer vision | image, video | detection | object-detection | deep-perm-set-net-learn-to-predict-sets-with | softmax |
| computer vision | image, video | detection | object-detection | deep-perm-set-net-learn-to-predict-sets-with | faster-r-cnn |
| computer vision | image, video | detection | object-detection | deep-perm-set-net-learn-to-predict-sets-with | rpn |
| computer vision | image, video | detection | object-detection | alphax-exploring-neural-architectures-with | random-search |
| computer vision | image, video | detection | object-detection | fssd-feature-fusion-single-shot-multibox | convolution |
| computer vision | image, video | detection | object-detection | fssd-feature-fusion-single-shot-multibox | ssd |
| computer vision | image, video | detection | object-detection | fssd-feature-fusion-single-shot-multibox | 1x1-convolution |
| computer vision | image, video | detection | object-detection | fssd-feature-fusion-single-shot-multibox | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | global-average-pooling |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | residual-block |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | convolution |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | max-pooling |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | 1x1-convolution |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | relu |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | he-initialization |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | batch-normalization |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | residual-connection |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | resnet |
| computer vision | image, video | detection | object-detection | resnet-sparsifier-learning-strict-identity | average-pooling |
| computer vision | image, video | detection | object-detection | object-detection-at-200-frames-per-second | relu |
| computer vision | image, video | detection | object-detection | object-detection-at-200-frames-per-second | dense-connections |
| computer vision | image, video | detection | object-detection | object-detection-at-200-frames-per-second | dropout |
| computer vision | image, video | detection | object-detection | object-detection-at-200-frames-per-second | convolution |
| computer vision | image, video | detection | object-detection | object-detection-at-200-frames-per-second | softmax |
| computer vision | image, video | detection | object-detection | object-detection-at-200-frames-per-second | vgg |
| computer vision | image, video | detection | object-detection | object-detection-at-200-frames-per-second | max-pooling |
| computer vision | image, video | detection | object-detection | learning-rich-features-for-image-manipulation | roi-pooling |
| computer vision | image, video | detection | object-detection | learning-rich-features-for-image-manipulation | convolution |
| computer vision | image, video | detection | object-detection | learning-rich-features-for-image-manipulation | softmax |
| computer vision | image, video | detection | object-detection | learning-rich-features-for-image-manipulation | faster-r-cnn |
| computer vision | image, video | detection | object-detection | learning-rich-features-for-image-manipulation | rpn |
| computer vision | image, video | detection | object-detection | detecting-traffic-lights-by-single-shot | convolution |
| computer vision | image, video | detection | object-detection | detecting-traffic-lights-by-single-shot | ssd |
| computer vision | image, video | detection | object-detection | detecting-traffic-lights-by-single-shot | 1x1-convolution |
| computer vision | image, video | detection | object-detection | detecting-traffic-lights-by-single-shot | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | global-average-pooling |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | softmax |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | convolution |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | max-pooling |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | 1x1-convolution |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | fire-module |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | relu |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | dropout |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | xavier-initialization |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | residual-connection |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | squeezenet |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | dcnn |
| computer vision | image, video | detection | object-detection | squeezejet-high-level-synthesis-accelerator | average-pooling |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | resnet |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | k-nn |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | rpn |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | average-pooling |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | dense-connections |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | alexnet |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | global-average-pooling |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | roi-pooling |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | vgg |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | faster-r-cnn |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | svm |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | grouped-convolution |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | fast-r-cnn |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | residual-connection |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | nt-xent |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | convolution |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | residual-block |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | softmax |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | local-response-normalization |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | max-pooling |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | 1x1-convolution |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | relu |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | he-initialization |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | dropout |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non | batch-normalization |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | average-pooling |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | global-average-pooling |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | convolution |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | 1x1-convolution |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | resnext |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | relu |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | resnext-block |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | he-initialization |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | grouped-convolution |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | batch-normalization |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | randomresizedcrop |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | exploring-the-limits-of-weakly-supervised | residual-connection |
| computer vision | image, video | detection | object-detection | algorithms-for-semantic-segmentation-of | dcnn |
| computer vision | image, video | detection | object-detection | dsod-learning-deeply-supervised-object | convolution |
| computer vision | image, video | detection | object-detection | dsod-learning-deeply-supervised-object | ssd |
| computer vision | image, video | detection | object-detection | dsod-learning-deeply-supervised-object | 1x1-convolution |
| computer vision | image, video | detection | object-detection | dsod-learning-deeply-supervised-object | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | temporally-identity-aware-ssd-with | tanh-activation |
| computer vision | image, video | detection | object-detection | temporally-identity-aware-ssd-with | convolution |
| computer vision | image, video | detection | object-detection | temporally-identity-aware-ssd-with | sigmoid-activation |
| computer vision | image, video | detection | object-detection | temporally-identity-aware-ssd-with | convlstm |
| computer vision | image, video | detection | object-detection | temporally-identity-aware-ssd-with | temporal-attention |
| computer vision | image, video | detection | object-detection | applying-faster-r-cnn-for-object-detection-on | roi-pooling |
| computer vision | image, video | detection | object-detection | applying-faster-r-cnn-for-object-detection-on | convolution |
| computer vision | image, video | detection | object-detection | applying-faster-r-cnn-for-object-detection-on | softmax |
| computer vision | image, video | detection | object-detection | applying-faster-r-cnn-for-object-detection-on | faster-r-cnn |
| computer vision | image, video | detection | object-detection | applying-faster-r-cnn-for-object-detection-on | rpn |
| computer vision | image, video | detection | object-detection | smart-surveillance-as-an-edge-network-service | convolution |
| computer vision | image, video | detection | object-detection | smart-surveillance-as-an-edge-network-service | svm |
| computer vision | image, video | detection | object-detection | deep-cross-domain-building-extraction-for | roi-pooling |
| computer vision | image, video | detection | object-detection | deep-cross-domain-building-extraction-for | convolution |
| computer vision | image, video | detection | object-detection | deep-cross-domain-building-extraction-for | softmax |
| computer vision | image, video | detection | object-detection | deep-cross-domain-building-extraction-for | faster-r-cnn |
| computer vision | image, video | detection | object-detection | deep-cross-domain-building-extraction-for | rpn |
| computer vision | image, video | detection | object-detection | rethinking-the-faster-r-cnn-architecture-for | roi-pooling |
| computer vision | image, video | detection | object-detection | rethinking-the-faster-r-cnn-architecture-for | convolution |
| computer vision | image, video | detection | object-detection | rethinking-the-faster-r-cnn-architecture-for | softmax |
| computer vision | image, video | detection | object-detection | rethinking-the-faster-r-cnn-architecture-for | faster-r-cnn |
| computer vision | image, video | detection | object-detection | rethinking-the-faster-r-cnn-architecture-for | rpn |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | roi-align |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | convolution |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | softmax |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | weight-decay |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | 1x1-convolution |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | relu |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | step-decay |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | batch-normalization |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | fpn |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | dilated-convolution |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | dilated-bottleneck-with-projection-block |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | average-pooling |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | rpn |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | global-average-pooling |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | dilated-bottleneck-block |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | roi-pooling |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | faster-r-cnn |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | residual-connection |
| computer vision | image, video | detection | object-detection | detnet-a-backbone-network-for-object | detnet |
| computer vision | image, video | detection | object-detection | dropout-sampling-for-robust-object-detection | dropout |
| computer vision | image, video | detection | object-detection | weakly-supervised-object-discovery-by | gan |
| computer vision | image, video | detection | object-detection | weakly-supervised-object-discovery-by | convolution |
| computer vision | image, video | detection | object-detection | towards-high-performance-video-object | gru |
| computer vision | image, video | detection | object-detection | shapeshifter-robust-physical-adversarial | roi-pooling |
| computer vision | image, video | detection | object-detection | shapeshifter-robust-physical-adversarial | softmax |
| computer vision | image, video | detection | object-detection | shapeshifter-robust-physical-adversarial | convolution |
| computer vision | image, video | detection | object-detection | shapeshifter-robust-physical-adversarial | faster-r-cnn |
| computer vision | image, video | detection | object-detection | shapeshifter-robust-physical-adversarial | rpn |
| computer vision | image, video | detection | object-detection | hyperfusion-net-densely-reflective-fusion-for | hierarchical-feature-fusion |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | convolution |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | residual-block |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | max-pooling |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | non-local-operation |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | embedded-dot-product-affinity |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | weight-decay |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | 1x1-convolution |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | resnext |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | relu |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | he-initialization |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | concatenation-affinity |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | batch-normalization |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | resnet |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | embedded-gaussian-affinity |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | average-pooling |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | global-average-pooling |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | resnext-block |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | grouped-convolution |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | residual-connection |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | non-local-neural-networks | non-local-block |
| computer vision | image, video | detection | object-detection | megdet-a-large-mini-batch-object-detector | 1x1-convolution |
| computer vision | image, video | detection | object-detection | megdet-a-large-mini-batch-object-detector | retinanet |
| computer vision | image, video | detection | object-detection | megdet-a-large-mini-batch-object-detector | batch-normalization |
| computer vision | image, video | detection | object-detection | megdet-a-large-mini-batch-object-detector | mask-r-cnn |
| computer vision | image, video | detection | object-detection | megdet-a-large-mini-batch-object-detector | fpn |
| computer vision | image, video | detection | object-detection | megdet-a-large-mini-batch-object-detector | roi-align |
| computer vision | image, video | detection | object-detection | megdet-a-large-mini-batch-object-detector | convolution |
| computer vision | image, video | detection | object-detection | megdet-a-large-mini-batch-object-detector | softmax |
| computer vision | image, video | detection | object-detection | megdet-a-large-mini-batch-object-detector | focal-loss |
| computer vision | image, video | detection | object-detection | deblurgan-blind-motion-deblurring-using | gan |
| computer vision | image, video | detection | object-detection | deblurgan-blind-motion-deblurring-using | convolution |
| computer vision | image, video | detection | object-detection | exploring-multi-branch-and-high-level | convolution |
| computer vision | image, video | detection | object-detection | exploring-multi-branch-and-high-level | dilated-convolution |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | deeplabv3 |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | dilated-convolution |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | relu6 |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | average-pooling |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | rmsprop |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | depthwise-separable-convolution |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | aspp |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | depthwise-convolution |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | residual-connection |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | pointwise-convolution |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | residual-block |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | convolution |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | weight-decay |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | mobilenetv2 |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | 1x1-convolution |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | relu |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | spatial-pyramid-pooling |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | inverted-residual-block |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | dropout |
| computer vision | image, video | detection | object-detection | mobilenetv2-inverted-residuals-and-linear | batch-normalization |
| computer vision | image, video | detection | object-detection | regional-priority-based-anomaly-detection | autoencoder |
| computer vision | image, video | detection | object-detection | multi-scale-location-aware-kernel | roi-pooling |
| computer vision | image, video | detection | object-detection | multi-scale-location-aware-kernel | convolution |
| computer vision | image, video | detection | object-detection | multi-scale-location-aware-kernel | softmax |
| computer vision | image, video | detection | object-detection | multi-scale-location-aware-kernel | faster-r-cnn |
| computer vision | image, video | detection | object-detection | multi-scale-location-aware-kernel | rpn |
| computer vision | image, video | detection | object-detection | contrast-oriented-deep-neural-networks-for | crf |
| computer vision | image, video | detection | object-detection | deep-learning-object-detection-methods-for | roi-pooling |
| computer vision | image, video | detection | object-detection | deep-learning-object-detection-methods-for | convolution |
| computer vision | image, video | detection | object-detection | deep-learning-object-detection-methods-for | softmax |
| computer vision | image, video | detection | object-detection | deep-learning-object-detection-methods-for | faster-r-cnn |
| computer vision | image, video | detection | object-detection | deep-learning-object-detection-methods-for | rpn |
| computer vision | image, video | detection | object-detection | pose2seg-detection-free-human-instance | roi-align |
| computer vision | image, video | detection | object-detection | pose2seg-detection-free-human-instance | convolution |
| computer vision | image, video | detection | object-detection | pose2seg-detection-free-human-instance | softmax |
| computer vision | image, video | detection | object-detection | deep-regionlets-for-object-detection | mask-r-cnn |
| computer vision | image, video | detection | object-detection | deep-regionlets-for-object-detection | roi-align |
| computer vision | image, video | detection | object-detection | deep-regionlets-for-object-detection | convolution |
| computer vision | image, video | detection | object-detection | deep-regionlets-for-object-detection | softmax |
| computer vision | image, video | detection | object-detection | context-aware-single-shot-detector | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | context-aware-single-shot-detector | convolution |
| computer vision | image, video | detection | object-detection | context-aware-single-shot-detector | dilated-convolution |
| computer vision | image, video | detection | object-detection | context-aware-single-shot-detector | ssd |
| computer vision | image, video | detection | object-detection | context-aware-single-shot-detector | 1x1-convolution |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | yolov2 |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | average-pooling |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | dense-connections |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | alexnet |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | global-average-pooling |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | darknet-19 |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | grouped-convolution |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | vgg-16 |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | softmax |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | local-response-normalization |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | convolution |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | max-pooling |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | 1x1-convolution |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | relu |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | dropout |
| computer vision | image, video | detection | object-detection | iterative-low-rank-approximation-for-cnn | batch-normalization |
| computer vision | image, video | detection | object-detection | zero-shot-detection | yolov2 |
| computer vision | image, video | detection | object-detection | zero-shot-detection | average-pooling |
| computer vision | image, video | detection | object-detection | zero-shot-detection | global-average-pooling |
| computer vision | image, video | detection | object-detection | zero-shot-detection | convolution |
| computer vision | image, video | detection | object-detection | zero-shot-detection | softmax |
| computer vision | image, video | detection | object-detection | zero-shot-detection | max-pooling |
| computer vision | image, video | detection | object-detection | zero-shot-detection | darknet-19 |
| computer vision | image, video | detection | object-detection | zero-shot-detection | 1x1-convolution |
| computer vision | image, video | detection | object-detection | zero-shot-detection | batch-normalization |
| computer vision | image, video | detection | object-detection | weakly-supervised-object-localization-on | convolution |
| computer vision | image, video | detection | object-detection | weakly-supervised-object-localization-on | fcn |
| computer vision | image, video | detection | object-detection | weakly-supervised-object-localization-on | max-pooling |
| computer vision | image, video | detection | object-detection | complex-yolo-real-time-3d-object-detection-on | yolov2 |
| computer vision | image, video | detection | object-detection | complex-yolo-real-time-3d-object-detection-on | average-pooling |
| computer vision | image, video | detection | object-detection | complex-yolo-real-time-3d-object-detection-on | global-average-pooling |
| computer vision | image, video | detection | object-detection | complex-yolo-real-time-3d-object-detection-on | convolution |
| computer vision | image, video | detection | object-detection | complex-yolo-real-time-3d-object-detection-on | softmax |
| computer vision | image, video | detection | object-detection | complex-yolo-real-time-3d-object-detection-on | max-pooling |
| computer vision | image, video | detection | object-detection | complex-yolo-real-time-3d-object-detection-on | darknet-19 |
| computer vision | image, video | detection | object-detection | complex-yolo-real-time-3d-object-detection-on | 1x1-convolution |
| computer vision | image, video | detection | object-detection | complex-yolo-real-time-3d-object-detection-on | batch-normalization |
| computer vision | image, video | detection | object-detection | deeply-supervised-salient-object-detection | convolution |
| computer vision | image, video | detection | object-detection | deeply-supervised-salient-object-detection | fcn |
| computer vision | image, video | detection | object-detection | deeply-supervised-salient-object-detection | max-pooling |
| computer vision | image, video | detection | object-detection | domain-adaptive-faster-r-cnn-for-object | roi-pooling |
| computer vision | image, video | detection | object-detection | domain-adaptive-faster-r-cnn-for-object | convolution |
| computer vision | image, video | detection | object-detection | domain-adaptive-faster-r-cnn-for-object | softmax |
| computer vision | image, video | detection | object-detection | domain-adaptive-faster-r-cnn-for-object | faster-r-cnn |
| computer vision | image, video | detection | object-detection | domain-adaptive-faster-r-cnn-for-object | rpn |
| computer vision | image, video | detection | object-detection | joint-3d-proposal-generation-and-object | rpn |
| computer vision | image, video | detection | object-detection | cnn-based-automatic-urinary-particles | ssd |
| computer vision | image, video | detection | object-detection | cnn-based-automatic-urinary-particles | rpn |
| computer vision | image, video | detection | object-detection | cnn-based-automatic-urinary-particles | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | cnn-based-automatic-urinary-particles | roi-pooling |
| computer vision | image, video | detection | object-detection | cnn-based-automatic-urinary-particles | convolution |
| computer vision | image, video | detection | object-detection | cnn-based-automatic-urinary-particles | softmax |
| computer vision | image, video | detection | object-detection | cnn-based-automatic-urinary-particles | faster-r-cnn |
| computer vision | image, video | detection | object-detection | cnn-based-automatic-urinary-particles | 1x1-convolution |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | resnext-block |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | grouped-convolution |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | residual-connection |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | adaptive-feature-pooling |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | bottom-up-path-augmentation |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | roi-align |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | convolution |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | residual-block |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | max-pooling |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | weight-decay |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | 1x1-convolution |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | resnext |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | relu |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | panet |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | he-initialization |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | batch-normalization |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | fpn |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | resnet |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | pafpn |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | average-pooling |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | rpn |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | dense-connections |
| computer vision | image, video | detection | object-detection | path-aggregation-network-for-instance | global-average-pooling |
| computer vision | image, video | detection | object-detection | lstd-a-low-shot-transfer-detector-for-object | convolution |
| computer vision | image, video | detection | object-detection | lstd-a-low-shot-transfer-detector-for-object | ssd |
| computer vision | image, video | detection | object-detection | lstd-a-low-shot-transfer-detector-for-object | 1x1-convolution |
| computer vision | image, video | detection | object-detection | lstd-a-low-shot-transfer-detector-for-object | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | focal-loss-dense-detector-for-vehicle | fpn |
| computer vision | image, video | detection | object-detection | focal-loss-dense-detector-for-vehicle | convolution |
| computer vision | image, video | detection | object-detection | focal-loss-dense-detector-for-vehicle | focal-loss |
| computer vision | image, video | detection | object-detection | focal-loss-dense-detector-for-vehicle | 1x1-convolution |
| computer vision | image, video | detection | object-detection | focal-loss-dense-detector-for-vehicle | retinanet |
| computer vision | image, video | detection | object-detection | deep-6dpose-recovering-6d-object-pose-from-a | mask-r-cnn |
| computer vision | image, video | detection | object-detection | deep-6dpose-recovering-6d-object-pose-from-a | roi-align |
| computer vision | image, video | detection | object-detection | deep-6dpose-recovering-6d-object-pose-from-a | convolution |
| computer vision | image, video | detection | object-detection | deep-6dpose-recovering-6d-object-pose-from-a | softmax |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | resnet |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | average-pooling |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | dense-connections |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | alexnet |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | global-average-pooling |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | grouped-convolution |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | residual-connection |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | bottleneck-residual-block |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | softmax |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | local-response-normalization |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | residual-block |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | convolution |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | max-pooling |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | 1x1-convolution |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | relu |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | dropout |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | he-initialization |
| computer vision | image, video | detection | reasoning | recurrent-residual-module-for-fast-inference | batch-normalization |
| computer vision | image, video | detection | object-detection | scale-optimization-for-full-image-cnn-vehicle | roi-pooling |
| computer vision | image, video | detection | object-detection | scale-optimization-for-full-image-cnn-vehicle | convolution |
| computer vision | image, video | detection | object-detection | scale-optimization-for-full-image-cnn-vehicle | softmax |
| computer vision | image, video | detection | object-detection | scale-optimization-for-full-image-cnn-vehicle | faster-r-cnn |
| computer vision | image, video | detection | object-detection | scale-optimization-for-full-image-cnn-vehicle | rpn |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | global-average-pooling |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | softmax |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | convolution |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | max-pooling |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | 1x1-convolution |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | fire-module |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | relu |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | dropout |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | xavier-initialization |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | residual-connection |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | squeezenet |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | ssd |
| computer vision | image, video | detection | object-detection | tiny-ssd-a-tiny-single-shot-detection-deep | average-pooling |
| computer vision | image, video | detection | object-detection | 3d-regression-neural-network-for-the | convolution |
| computer vision | image, video | detection | object-detection | object-detection-with-mask-based-feature | roi-pooling |
| computer vision | image, video | detection | object-detection | object-detection-with-mask-based-feature | convolution |
| computer vision | image, video | detection | object-detection | object-detection-with-mask-based-feature | softmax |
| computer vision | image, video | detection | object-detection | object-detection-with-mask-based-feature | faster-r-cnn |
| computer vision | image, video | detection | object-detection | object-detection-with-mask-based-feature | rpn |
| computer vision | image, video | detection | object-detection | vehicle-detection-in-aerial-images | focal-loss |
| computer vision | image, video | detection | object-detection | saliency-enhanced-robust-visual-tracking | convolution |
| computer vision | image, video | detection | object-detection | recovering-from-random-pruning-on-the | vgg-16 |
| computer vision | image, video | detection | object-detection | sliding-line-point-regression-for-shape | rpn |
| computer vision | image, video | detection | object-detection | sliding-line-point-regression-for-shape | r-fcn |
| computer vision | image, video | detection | object-detection | sliding-line-point-regression-for-shape | roi-pooling |
| computer vision | image, video | detection | object-detection | sliding-line-point-regression-for-shape | convolution |
| computer vision | image, video | detection | object-detection | sliding-line-point-regression-for-shape | softmax |
| computer vision | image, video | detection | object-detection | sliding-line-point-regression-for-shape | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | sliding-line-point-regression-for-shape | faster-r-cnn |
| computer vision | image, video | detection | object-detection | weakly-supervised-object-detection-with | softmax |
| computer vision | image, video | detection | object-detection | mask-r-cnn | roi-align |
| computer vision | image, video | detection | object-detection | mask-r-cnn | convolution |
| computer vision | image, video | detection | object-detection | mask-r-cnn | softmax |
| computer vision | image, video | detection | object-detection | mask-r-cnn | residual-block |
| computer vision | image, video | detection | object-detection | mask-r-cnn | max-pooling |
| computer vision | image, video | detection | object-detection | mask-r-cnn | 1x1-convolution |
| computer vision | image, video | detection | object-detection | mask-r-cnn | resnext |
| computer vision | image, video | detection | object-detection | mask-r-cnn | relu |
| computer vision | image, video | detection | object-detection | mask-r-cnn | he-initialization |
| computer vision | image, video | detection | object-detection | mask-r-cnn | batch-normalization |
| computer vision | image, video | detection | object-detection | mask-r-cnn | mask-r-cnn |
| computer vision | image, video | detection | object-detection | mask-r-cnn | resnet |
| computer vision | image, video | detection | object-detection | mask-r-cnn | average-pooling |
| computer vision | image, video | detection | object-detection | mask-r-cnn | global-average-pooling |
| computer vision | image, video | detection | object-detection | mask-r-cnn | resnext-block |
| computer vision | image, video | detection | object-detection | mask-r-cnn | grouped-convolution |
| computer vision | image, video | detection | object-detection | mask-r-cnn | residual-connection |
| computer vision | image, video | detection | object-detection | mask-r-cnn | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | extend-the-shallow-part-of-single-shot | convolution |
| computer vision | image, video | detection | object-detection | extend-the-shallow-part-of-single-shot | ssd |
| computer vision | image, video | detection | object-detection | extend-the-shallow-part-of-single-shot | 1x1-convolution |
| computer vision | image, video | detection | object-detection | extend-the-shallow-part-of-single-shot | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | yolov2 |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | average-pooling |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | dense-connections |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | alexnet |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | global-average-pooling |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | darknet-19 |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | grouped-convolution |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | softmax |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | local-response-normalization |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | convolution |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | max-pooling |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | 1x1-convolution |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | relu |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | dropout |
| computer vision | image, video | detection | object-detection | stressednets-efficient-feature | batch-normalization |
| computer vision | image, video | detection | object-detection | an-accurate-and-real-time-self-blast-glass | fast-r-cnn |
| computer vision | image, video | detection | object-detection | an-accurate-and-real-time-self-blast-glass | roi-pooling |
| computer vision | image, video | detection | object-detection | an-accurate-and-real-time-self-blast-glass | softmax |
| computer vision | image, video | detection | object-detection | an-accurate-and-real-time-self-blast-glass | convolution |
| computer vision | image, video | detection | object-detection | msdnn-multi-scale-deep-neural-network-for | convolution |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | resnet |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | average-pooling |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | dense-connections |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | global-average-pooling |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | vgg |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | residual-connection |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | convolution |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | residual-block |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | softmax |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | max-pooling |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | 1x1-convolution |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | relu |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | he-initialization |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | dropout |
| computer vision | image, video | detection | object-detection | single-shot-refinement-neural-network-for | batch-normalization |
| computer vision | image, video | detection | object-detection | automated-flow-for-compressing-convolution | yolov2 |
| computer vision | image, video | detection | object-detection | automated-flow-for-compressing-convolution | average-pooling |
| computer vision | image, video | detection | object-detection | automated-flow-for-compressing-convolution | global-average-pooling |
| computer vision | image, video | detection | object-detection | automated-flow-for-compressing-convolution | convolution |
| computer vision | image, video | detection | object-detection | automated-flow-for-compressing-convolution | softmax |
| computer vision | image, video | detection | object-detection | automated-flow-for-compressing-convolution | max-pooling |
| computer vision | image, video | detection | object-detection | automated-flow-for-compressing-convolution | darknet-19 |
| computer vision | image, video | detection | object-detection | automated-flow-for-compressing-convolution | 1x1-convolution |
| computer vision | image, video | detection | object-detection | automated-flow-for-compressing-convolution | batch-normalization |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | global-average-pooling |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | convolution |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | residual-block |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | max-pooling |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | 1x1-convolution |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | relu |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | he-initialization |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | batch-normalization |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | residual-connection |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | resnet |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | dilated-convolution |
| computer vision | image, video | detection | object-detection | masklab-instance-segmentation-by-refining | average-pooling |
| computer vision | image, video | detection | object-detection | symbol-detection-in-online-handwritten | roi-pooling |
| computer vision | image, video | detection | object-detection | symbol-detection-in-online-handwritten | convolution |
| computer vision | image, video | detection | object-detection | symbol-detection-in-online-handwritten | softmax |
| computer vision | image, video | detection | object-detection | symbol-detection-in-online-handwritten | faster-r-cnn |
| computer vision | image, video | detection | object-detection | symbol-detection-in-online-handwritten | rpn |
| computer vision | image, video | detection | object-detection | data-distillation-towards-omni-supervised | fpn |
| computer vision | image, video | detection | object-detection | data-distillation-towards-omni-supervised | mask-r-cnn |
| computer vision | image, video | detection | object-detection | data-distillation-towards-omni-supervised | rpn |
| computer vision | image, video | detection | object-detection | data-distillation-towards-omni-supervised | roi-pooling |
| computer vision | image, video | detection | object-detection | data-distillation-towards-omni-supervised | roi-align |
| computer vision | image, video | detection | object-detection | data-distillation-towards-omni-supervised | convolution |
| computer vision | image, video | detection | object-detection | data-distillation-towards-omni-supervised | softmax |
| computer vision | image, video | detection | object-detection | data-distillation-towards-omni-supervised | faster-r-cnn |
| computer vision | image, video | detection | object-detection | data-distillation-towards-omni-supervised | 1x1-convolution |
| computer vision | image, video | detection | object-detection | compiling-deep-learning-models-for-custom | dense-connections |
| computer vision | image, video | detection | object-detection | compiling-deep-learning-models-for-custom | alexnet |
| computer vision | image, video | detection | object-detection | compiling-deep-learning-models-for-custom | softmax |
| computer vision | image, video | detection | object-detection | compiling-deep-learning-models-for-custom | local-response-normalization |
| computer vision | image, video | detection | object-detection | compiling-deep-learning-models-for-custom | convolution |
| computer vision | image, video | detection | object-detection | compiling-deep-learning-models-for-custom | max-pooling |
| computer vision | image, video | detection | object-detection | compiling-deep-learning-models-for-custom | 1x1-convolution |
| computer vision | image, video | detection | object-detection | compiling-deep-learning-models-for-custom | relu |
| computer vision | image, video | detection | object-detection | compiling-deep-learning-models-for-custom | dropout |
| computer vision | image, video | detection | object-detection | compiling-deep-learning-models-for-custom | grouped-convolution |
| computer vision | image, video | detection | object-detection | weaving-multi-scale-context-for-single-shot | convolution |
| computer vision | image, video | detection | object-detection | weaving-multi-scale-context-for-single-shot | ssd |
| computer vision | image, video | detection | object-detection | weaving-multi-scale-context-for-single-shot | 1x1-convolution |
| computer vision | image, video | detection | object-detection | weaving-multi-scale-context-for-single-shot | batch-normalization |
| computer vision | image, video | detection | object-detection | weaving-multi-scale-context-for-single-shot | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | average-pooling |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | rpn |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | dense-connections |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | alexnet |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | global-average-pooling |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | roi-pooling |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | channel-shuffle |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | faster-r-cnn |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | residual-connection |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | pointwise-convolution |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | softmax |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | local-response-normalization |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | shufflenet-block |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | weight-decay |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | 1x1-convolution |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | dropout |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | randomresizedcrop |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | depthwise-convolution |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | grouped-convolution |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | convolution |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | shufflenet |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | max-pooling |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | relu |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | step-decay |
| computer vision | image, video | detection | object-detection | shufflenet-an-extremely-efficient | batch-normalization |
| computer vision | image, video | detection | object-detection | deep-generative-adversarial-compression | gan |
| computer vision | image, video | detection | object-detection | deep-generative-adversarial-compression | convolution |
| computer vision | image, video | detection | object-detection | clusternet-detecting-small-objects-in-large | roi-pooling |
| computer vision | image, video | detection | object-detection | clusternet-detecting-small-objects-in-large | convolution |
| computer vision | image, video | detection | object-detection | clusternet-detecting-small-objects-in-large | softmax |
| computer vision | image, video | detection | object-detection | clusternet-detecting-small-objects-in-large | faster-r-cnn |
| computer vision | image, video | detection | object-detection | clusternet-detecting-small-objects-in-large | rpn |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | convolution |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | residual-block |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | max-pooling |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | group-normalization |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | resnext |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | relu |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | r-fcn |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | he-initialization |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | batch-normalization |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | fpn |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | rpn |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | average-pooling |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | dense-connections |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | global-average-pooling |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | roi-pooling |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | faster-r-cnn |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | residual-connection |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | roi-align |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | softmax |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | cascade-r-cnn |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | 1x1-convolution |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | dropout |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | resnet |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | vgg |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | cascade-mask-r-cnn |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | resnext-block |
| computer vision | image, video | detection | object-detection | cascade-r-cnn-delving-into-high-quality | grouped-convolution |
| computer vision | image, video | detection | object-detection | automatic-recognition-of-coal-and-gangue | dense-connections |
| computer vision | image, video | detection | object-detection | automatic-recognition-of-coal-and-gangue | alexnet |
| computer vision | image, video | detection | object-detection | automatic-recognition-of-coal-and-gangue | convolution |
| computer vision | image, video | detection | object-detection | automatic-recognition-of-coal-and-gangue | softmax |
| computer vision | image, video | detection | object-detection | automatic-recognition-of-coal-and-gangue | local-response-normalization |
| computer vision | image, video | detection | object-detection | automatic-recognition-of-coal-and-gangue | max-pooling |
| computer vision | image, video | detection | object-detection | automatic-recognition-of-coal-and-gangue | svm |
| computer vision | image, video | detection | object-detection | automatic-recognition-of-coal-and-gangue | 1x1-convolution |
| computer vision | image, video | detection | object-detection | automatic-recognition-of-coal-and-gangue | relu |
| computer vision | image, video | detection | object-detection | automatic-recognition-of-coal-and-gangue | dropout |
| computer vision | image, video | detection | object-detection | automatic-recognition-of-coal-and-gangue | grouped-convolution |
| computer vision | image, video | detection | object-detection | me-r-cnn-multi-expert-r-cnn-for-object | selective-search |
| computer vision | image, video | detection | object-detection | sparse-coding-on-stereo-video-for-object | dcnn |
| computer vision | image, video | detection | object-detection | multi-channel-cnn-based-object-detection-for | fast-r-cnn |
| computer vision | image, video | detection | object-detection | multi-channel-cnn-based-object-detection-for | roi-pooling |
| computer vision | image, video | detection | object-detection | multi-channel-cnn-based-object-detection-for | convolution |
| computer vision | image, video | detection | object-detection | multi-channel-cnn-based-object-detection-for | softmax |
| computer vision | image, video | detection | object-detection | discriminative-learning-of-open-vocabulary | roi-pooling |
| computer vision | image, video | detection | object-detection | discriminative-learning-of-open-vocabulary | convolution |
| computer vision | image, video | detection | object-detection | discriminative-learning-of-open-vocabulary | softmax |
| computer vision | image, video | detection | object-detection | discriminative-learning-of-open-vocabulary | faster-r-cnn |
| computer vision | image, video | detection | object-detection | discriminative-learning-of-open-vocabulary | rpn |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | googlenet |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | average-pooling |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | dense-connections |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | inception-module |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | softmax |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | local-response-normalization |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | convolution |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | max-pooling |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | 1x1-convolution |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | relu |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | dropout |
| computer vision | image, video | detection | object-detection | feature-selective-networks-for-object | auxiliary-classifier |
| computer vision | image, video | detection | object-detection | random-erasing-data-augmentation | random-erasing |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | global-average-pooling |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | convolution |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | residual-block |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | max-pooling |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | 1x1-convolution |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | relu |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | he-initialization |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | batch-normalization |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | residual-connection |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | resnet |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | knowledge-distillation |
| computer vision | image, video | detection | object-detection | apprentice-using-knowledge-distillation | average-pooling |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | sigmoid-activation |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | squeeze-and-excitation-block |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | roi-align |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | convolution |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | residual-block |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | softmax |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | max-pooling |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | 1x1-convolution |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | resnext |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | relu |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | dense-block |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | he-initialization |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | dropout |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | batch-normalization |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | mask-r-cnn |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | resnet |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | average-pooling |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | dense-connections |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | global-average-pooling |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | senet |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | concatenated-skip-connection |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | densenet |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | resnext-block |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | grouped-convolution |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | residual-connection |
| computer vision | image, video | detection | object-detection | learning-deep-compositional-grammatical | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | squeeze-segnet-a-new-fast-deep-convolutional | segnet |
| computer vision | image, video | detection | object-detection | squeeze-segnet-a-new-fast-deep-convolutional | relu |
| computer vision | image, video | detection | object-detection | squeeze-segnet-a-new-fast-deep-convolutional | he-initialization |
| computer vision | image, video | detection | object-detection | squeeze-segnet-a-new-fast-deep-convolutional | batch-normalization |
| computer vision | image, video | detection | object-detection | squeeze-segnet-a-new-fast-deep-convolutional | softmax |
| computer vision | image, video | detection | object-detection | squeeze-segnet-a-new-fast-deep-convolutional | convolution |
| computer vision | image, video | detection | object-detection | squeeze-segnet-a-new-fast-deep-convolutional | max-pooling |
| computer vision | image, video | detection | object-detection | towards-interpretable-r-cnn-by-unfolding | convolution |
| computer vision | image, video | detection | object-detection | towards-interpretable-r-cnn-by-unfolding | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | towards-interpretable-r-cnn-by-unfolding | r-fcn |
| computer vision | image, video | detection | object-detection | detecting-and-classifying-lesions-in | roi-pooling |
| computer vision | image, video | detection | object-detection | detecting-and-classifying-lesions-in | softmax |
| computer vision | image, video | detection | object-detection | detecting-and-classifying-lesions-in | convolution |
| computer vision | image, video | detection | object-detection | detecting-and-classifying-lesions-in | faster-r-cnn |
| computer vision | image, video | detection | object-detection | detecting-and-classifying-lesions-in | rpn |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | dense-connections |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | label-smoothing |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | transformer |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | multi-head-attention |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | residual-connection |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | layer-normalization |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | scaled |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | spatial-transformer |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | softmax |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | position-wise-feed-forward-layer |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | adam |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | relu |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | absolute-position-encodings |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | dropout |
| computer vision | image, video | detection | object-detection | image-patch-matching-using-convolutional | bpe |
| computer vision | image, video | detection | object-detection | feature-fused-ssd-fast-detection-for-small | convolution |
| computer vision | image, video | detection | object-detection | feature-fused-ssd-fast-detection-for-small | ssd |
| computer vision | image, video | detection | object-detection | feature-fused-ssd-fast-detection-for-small | 1x1-convolution |
| computer vision | image, video | detection | object-detection | feature-fused-ssd-fast-detection-for-small | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | edge-preserving-and-multi-scale-contextual | fast-r-cnn |
| computer vision | image, video | detection | object-detection | edge-preserving-and-multi-scale-contextual | roi-pooling |
| computer vision | image, video | detection | object-detection | edge-preserving-and-multi-scale-contextual | convolution |
| computer vision | image, video | detection | object-detection | edge-preserving-and-multi-scale-contextual | softmax |
| computer vision | image, video | detection | object-detection | fast-yolo-a-fast-you-only-look-once-system | yolov2 |
| computer vision | image, video | detection | object-detection | fast-yolo-a-fast-you-only-look-once-system | average-pooling |
| computer vision | image, video | detection | object-detection | fast-yolo-a-fast-you-only-look-once-system | global-average-pooling |
| computer vision | image, video | detection | object-detection | fast-yolo-a-fast-you-only-look-once-system | convolution |
| computer vision | image, video | detection | object-detection | fast-yolo-a-fast-you-only-look-once-system | softmax |
| computer vision | image, video | detection | object-detection | fast-yolo-a-fast-you-only-look-once-system | max-pooling |
| computer vision | image, video | detection | object-detection | fast-yolo-a-fast-you-only-look-once-system | darknet-19 |
| computer vision | image, video | detection | object-detection | fast-yolo-a-fast-you-only-look-once-system | 1x1-convolution |
| computer vision | image, video | detection | object-detection | fast-yolo-a-fast-you-only-look-once-system | batch-normalization |
| computer vision | image, video | detection | object-detection | object-detection-using-deep-cnns-trained-on | early-stopping |
| computer vision | image, video | detection | object-detection | deep-fruit-detection-in-orchards | roi-pooling |
| computer vision | image, video | detection | object-detection | deep-fruit-detection-in-orchards | convolution |
| computer vision | image, video | detection | object-detection | deep-fruit-detection-in-orchards | softmax |
| computer vision | image, video | detection | object-detection | deep-fruit-detection-in-orchards | faster-r-cnn |
| computer vision | image, video | detection | object-detection | deep-fruit-detection-in-orchards | rpn |
| computer vision | image, video | detection | object-detection | gaussian-filter-in-crf-based-semantic | convolution |
| computer vision | image, video | detection | object-detection | gaussian-filter-in-crf-based-semantic | fcn |
| computer vision | image, video | detection | object-detection | gaussian-filter-in-crf-based-semantic | max-pooling |
| computer vision | image, video | detection | object-detection | gaussian-filter-in-crf-based-semantic | crf |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | 1x1-convolution |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | relu |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | he-initialization |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | batch-normalization |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | fpn |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | resnet |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | average-pooling |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | rpn |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | global-average-pooling |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | roi-pooling |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | faster-r-cnn |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | residual-connection |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | ssd |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | convolution |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | residual-block |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | softmax |
| computer vision | image, video | detection | object-detection | chainercv-a-library-for-deep-learning-in | max-pooling |
| computer vision | image, video | detection | object-detection | multiple-kernel-based-vehicle-tracking-using | convolution |
| computer vision | image, video | detection | object-detection | multiple-kernel-based-vehicle-tracking-using | ssd |
| computer vision | image, video | detection | object-detection | multiple-kernel-based-vehicle-tracking-using | 1x1-convolution |
| computer vision | image, video | detection | object-detection | multiple-kernel-based-vehicle-tracking-using | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | s-ohem-stratified-online-hard-example-mining | ohem |
| computer vision | image, video | detection | object-detection | transitive-invariance-for-self-supervised | roi-pooling |
| computer vision | image, video | detection | object-detection | transitive-invariance-for-self-supervised | convolution |
| computer vision | image, video | detection | object-detection | transitive-invariance-for-self-supervised | softmax |
| computer vision | image, video | detection | object-detection | transitive-invariance-for-self-supervised | faster-r-cnn |
| computer vision | image, video | detection | object-detection | transitive-invariance-for-self-supervised | rpn |
| computer vision | image, video | detection | object-detection | deep-steering-learning-end-to-end-driving | tanh-activation |
| computer vision | image, video | detection | object-detection | deep-steering-learning-end-to-end-driving | lstm |
| computer vision | image, video | detection | object-detection | deep-steering-learning-end-to-end-driving | sigmoid-activation |
| computer vision | image, video | detection | object-detection | couplenet-coupling-global-structure-with | convolution |
| computer vision | image, video | detection | object-detection | couplenet-coupling-global-structure-with | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | couplenet-coupling-global-structure-with | r-fcn |
| computer vision | image, video | detection | object-detection | soft-nms-improving-object-detection-with-one | convolution |
| computer vision | image, video | detection | object-detection | soft-nms-improving-object-detection-with-one | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | soft-nms-improving-object-detection-with-one | soft-nms |
| computer vision | image, video | detection | object-detection | soft-nms-improving-object-detection-with-one | r-fcn |
| computer vision | image, video | detection | object-detection | learning-to-segment-on-tiny-datasets-a-new | crf |
| computer vision | image, video | detection | object-detection | learning-uncertain-convolutional-features-for | dropout |
| computer vision | image, video | detection | object-detection | ppr-fcn-weakly-supervised-visual-relation | convolution |
| computer vision | image, video | detection | object-detection | ppr-fcn-weakly-supervised-visual-relation | fcn |
| computer vision | image, video | detection | object-detection | ppr-fcn-weakly-supervised-visual-relation | max-pooling |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | convolution |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | residual-block |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | softmax |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | max-pooling |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | weight-decay |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | 1x1-convolution |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | relu |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | he-initialization |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | xavier-initialization |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | step-decay |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | batch-normalization |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | resnet |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | rpn |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | average-pooling |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | global-average-pooling |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | roi-pooling |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | faster-r-cnn |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | rmsprop |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | revisiting-unreasonable-effectiveness-of-data | residual-connection |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | googlenet |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | average-pooling |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | rpn |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | dense-connections |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | roi-pooling |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | inception-module |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | faster-r-cnn |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | vgg |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | auxiliary-classifier |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | fast-r-cnn |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | convolution |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | softmax |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | local-response-normalization |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | max-pooling |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | 1x1-convolution |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | relu |
| computer vision | image, video | detection | object-detection | t-cnn-tubelets-with-convolutional-neural | dropout |
| computer vision | image, video | detection | object-detection | temporal-dynamic-graph-lstm-for-action-driven | tanh-activation |
| computer vision | image, video | detection | object-detection | temporal-dynamic-graph-lstm-for-action-driven | memory-network |
| computer vision | image, video | detection | object-detection | temporal-dynamic-graph-lstm-for-action-driven | lstm |
| computer vision | image, video | detection | object-detection | temporal-dynamic-graph-lstm-for-action-driven | sigmoid-activation |
| computer vision | image, video | detection | object-detection | tube-convolutional-neural-network-t-cnn-for | convolution |
| computer vision | image, video | detection | object-detection | tube-convolutional-neural-network-t-cnn-for | 3d-convolution |
| computer vision | image, video | detection | object-detection | deep-interactive-region-segmentation-and | convolution |
| computer vision | image, video | detection | object-detection | deep-interactive-region-segmentation-and | fcn |
| computer vision | image, video | detection | object-detection | deep-interactive-region-segmentation-and | max-pooling |
| computer vision | image, video | detection | object-detection | improving-robustness-of-feature | convolution |
| computer vision | image, video | detection | object-detection | an-all-in-one-network-for-dehazing-and-beyond | roi-pooling |
| computer vision | image, video | detection | object-detection | an-all-in-one-network-for-dehazing-and-beyond | convolution |
| computer vision | image, video | detection | object-detection | an-all-in-one-network-for-dehazing-and-beyond | softmax |
| computer vision | image, video | detection | object-detection | an-all-in-one-network-for-dehazing-and-beyond | faster-r-cnn |
| computer vision | image, video | detection | object-detection | an-all-in-one-network-for-dehazing-and-beyond | rpn |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | global-average-pooling |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | residual-block |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | convolution |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | max-pooling |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | 1x1-convolution |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | relu |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | he-initialization |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | batch-normalization |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | residual-connection |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | resnet |
| computer vision | image, video | detection | object-detection | wide-residual-inception-networks-for-real | average-pooling |
| computer vision | image, video | detection | object-detection | learning-semantic-part-based-models-from | r-cnn |
| computer vision | image, video | detection | object-detection | learning-semantic-part-based-models-from | convolution |
| computer vision | image, video | detection | object-detection | learning-semantic-part-based-models-from | max-pooling |
| computer vision | image, video | detection | object-detection | learning-semantic-part-based-models-from | svm |
| computer vision | image, video | detection | object-detection | ron-reverse-connection-with-objectness-prior | roi-pooling |
| computer vision | image, video | detection | object-detection | ron-reverse-connection-with-objectness-prior | vgg-16 |
| computer vision | image, video | detection | object-detection | ron-reverse-connection-with-objectness-prior | convolution |
| computer vision | image, video | detection | object-detection | ron-reverse-connection-with-objectness-prior | softmax |
| computer vision | image, video | detection | object-detection | ron-reverse-connection-with-objectness-prior | faster-r-cnn |
| computer vision | image, video | detection | object-detection | ron-reverse-connection-with-objectness-prior | rpn |
| computer vision | image, video | detection | object-detection | yes-net-an-effective-detector-based-on-global | yolov2 |
| computer vision | image, video | detection | object-detection | yes-net-an-effective-detector-based-on-global | ssd |
| computer vision | image, video | detection | object-detection | yes-net-an-effective-detector-based-on-global | average-pooling |
| computer vision | image, video | detection | object-detection | yes-net-an-effective-detector-based-on-global | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | yes-net-an-effective-detector-based-on-global | global-average-pooling |
| computer vision | image, video | detection | object-detection | yes-net-an-effective-detector-based-on-global | convolution |
| computer vision | image, video | detection | object-detection | yes-net-an-effective-detector-based-on-global | softmax |
| computer vision | image, video | detection | object-detection | yes-net-an-effective-detector-based-on-global | max-pooling |
| computer vision | image, video | detection | object-detection | yes-net-an-effective-detector-based-on-global | darknet-19 |
| computer vision | image, video | detection | object-detection | yes-net-an-effective-detector-based-on-global | 1x1-convolution |
| computer vision | image, video | detection | object-detection | yes-net-an-effective-detector-based-on-global | batch-normalization |
| computer vision | image, video | detection | object-detection | detecting-small-signs-from-large-images | vgg-16 |
| computer vision | image, video | detection | object-detection | perceptual-generative-adversarial-networks | gan |
| computer vision | image, video | detection | object-detection | perceptual-generative-adversarial-networks | convolution |
| computer vision | image, video | detection | object-detection | point-linking-network-for-object-detection | convolution |
| computer vision | image, video | detection | object-detection | point-linking-network-for-object-detection | ssd |
| computer vision | image, video | detection | object-detection | point-linking-network-for-object-detection | 1x1-convolution |
| computer vision | image, video | detection | object-detection | point-linking-network-for-object-detection | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | 1x1-convolution |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | relu |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | he-initialization |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | batch-normalization |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | deformable-roi-pooling |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | resnet |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | average-pooling |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | global-average-pooling |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | deformable-position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | deformable-convolution |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | residual-connection |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | deformable-convnets |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | convolution |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | residual-block |
| computer vision | image, video | detection | object-detection | deformable-convolutional-networks | max-pooling |
| computer vision | image, video | detection | object-detection | face-r-cnn | roi-pooling |
| computer vision | image, video | detection | object-detection | face-r-cnn | convolution |
| computer vision | image, video | detection | object-detection | face-r-cnn | softmax |
| computer vision | image, video | detection | object-detection | face-r-cnn | faster-r-cnn |
| computer vision | image, video | detection | object-detection | face-r-cnn | rpn |
| computer vision | image, video | detection | object-detection | recurrent-soft-attention-model-for-common | tanh-activation |
| computer vision | image, video | detection | object-detection | recurrent-soft-attention-model-for-common | lstm |
| computer vision | image, video | detection | object-detection | recurrent-soft-attention-model-for-common | sigmoid-activation |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | global-average-pooling |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | residual-block |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | convolution |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | max-pooling |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | 1x1-convolution |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | relu |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | he-initialization |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | batch-normalization |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | residual-connection |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | resnet |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | ssd |
| computer vision | image, video | detection | object-detection | enhancement-of-ssd-by-concatenating-feature | average-pooling |
| computer vision | image, video | detection | object-detection | residual-squeeze-vgg16 | convolution |
| computer vision | image, video | detection | object-detection | residual-squeeze-vgg16 | 1x1-convolution |
| computer vision | image, video | detection | object-detection | residual-squeeze-vgg16 | fire-module |
| computer vision | image, video | detection | object-detection | residual-squeeze-vgg16 | relu |
| computer vision | image, video | detection | object-detection | improving-small-object-proposals-for-company | roi-pooling |
| computer vision | image, video | detection | object-detection | improving-small-object-proposals-for-company | convolution |
| computer vision | image, video | detection | object-detection | improving-small-object-proposals-for-company | softmax |
| computer vision | image, video | detection | object-detection | improving-small-object-proposals-for-company | faster-r-cnn |
| computer vision | image, video | detection | object-detection | improving-small-object-proposals-for-company | rpn |
| computer vision | image, video | detection | object-detection | relief-r-cnn-utilizing-convolutional-features | r-cnn |
| computer vision | image, video | detection | object-detection | relief-r-cnn-utilizing-convolutional-features | convolution |
| computer vision | image, video | detection | object-detection | relief-r-cnn-utilizing-convolutional-features | max-pooling |
| computer vision | image, video | detection | object-detection | relief-r-cnn-utilizing-convolutional-features | svm |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | rpn |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | dense-connections |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | roi-pooling |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | faster-r-cnn |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | vgg |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | ssd |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | convolution |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | softmax |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | max-pooling |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | 1x1-convolution |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | r-fcn |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | relu |
| computer vision | image, video | detection | object-detection | speedaccuracy-trade-offs-for-modern | dropout |
| computer vision | image, video | detection | object-detection | feature-pyramid-networks-for-object-detection | roi-pooling |
| computer vision | image, video | detection | object-detection | feature-pyramid-networks-for-object-detection | fpn |
| computer vision | image, video | detection | object-detection | feature-pyramid-networks-for-object-detection | convolution |
| computer vision | image, video | detection | object-detection | feature-pyramid-networks-for-object-detection | softmax |
| computer vision | image, video | detection | object-detection | feature-pyramid-networks-for-object-detection | faster-r-cnn |
| computer vision | image, video | detection | object-detection | feature-pyramid-networks-for-object-detection | 1x1-convolution |
| computer vision | image, video | detection | object-detection | feature-pyramid-networks-for-object-detection | rpn |
| computer vision | image, video | detection | object-detection | accurate-single-stage-detector-using | rpn |
| computer vision | image, video | detection | object-detection | accurate-single-stage-detector-using | dense-connections |
| computer vision | image, video | detection | object-detection | accurate-single-stage-detector-using | roi-pooling |
| computer vision | image, video | detection | object-detection | accurate-single-stage-detector-using | vgg-16 |
| computer vision | image, video | detection | object-detection | accurate-single-stage-detector-using | convolution |
| computer vision | image, video | detection | object-detection | accurate-single-stage-detector-using | softmax |
| computer vision | image, video | detection | object-detection | accurate-single-stage-detector-using | max-pooling |
| computer vision | image, video | detection | object-detection | accurate-single-stage-detector-using | vgg |
| computer vision | image, video | detection | object-detection | accurate-single-stage-detector-using | faster-r-cnn |
| computer vision | image, video | detection | object-detection | accurate-single-stage-detector-using | relu |
| computer vision | image, video | detection | object-detection | accurate-single-stage-detector-using | dropout |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | average-pooling |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | dense-connections |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | global-average-pooling |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | mobilenetv1 |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | depthwise-separable-convolution |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | depthwise-convolution |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | pointwise-convolution |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | softmax |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | convolution |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | exponential-decay |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | 1x1-convolution |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | relu |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | randomresizedcrop |
| computer vision | image, video | detection | object-detection | mobilenets-efficient-convolutional-neural | batch-normalization |
| computer vision | image, video | detection | object-detection | spatial-memory-for-context-reasoning-in | memory-network |
| computer vision | image, video | detection | object-detection | learning-detection-with-diverse-proposals | roi-pooling |
| computer vision | image, video | detection | object-detection | learning-detection-with-diverse-proposals | convolution |
| computer vision | image, video | detection | object-detection | learning-detection-with-diverse-proposals | softmax |
| computer vision | image, video | detection | object-detection | learning-detection-with-diverse-proposals | faster-r-cnn |
| computer vision | image, video | detection | object-detection | learning-detection-with-diverse-proposals | rpn |
| computer vision | image, video | detection | object-detection | pixelwise-instance-segmentation-with-a | crf |
| computer vision | image, video | detection | object-detection | evolution-in-groups-a-deeper-look-at-synaptic | dense-connections |
| computer vision | image, video | detection | object-detection | evolution-in-groups-a-deeper-look-at-synaptic | alexnet |
| computer vision | image, video | detection | object-detection | evolution-in-groups-a-deeper-look-at-synaptic | softmax |
| computer vision | image, video | detection | object-detection | evolution-in-groups-a-deeper-look-at-synaptic | local-response-normalization |
| computer vision | image, video | detection | object-detection | evolution-in-groups-a-deeper-look-at-synaptic | convolution |
| computer vision | image, video | detection | object-detection | evolution-in-groups-a-deeper-look-at-synaptic | max-pooling |
| computer vision | image, video | detection | object-detection | evolution-in-groups-a-deeper-look-at-synaptic | 1x1-convolution |
| computer vision | image, video | detection | object-detection | evolution-in-groups-a-deeper-look-at-synaptic | relu |
| computer vision | image, video | detection | object-detection | evolution-in-groups-a-deeper-look-at-synaptic | dropout |
| computer vision | image, video | detection | object-detection | evolution-in-groups-a-deeper-look-at-synaptic | grouped-convolution |
| computer vision | image, video | detection | object-detection | cross-view-image-matching-for-geo | roi-pooling |
| computer vision | image, video | detection | object-detection | cross-view-image-matching-for-geo | convolution |
| computer vision | image, video | detection | object-detection | cross-view-image-matching-for-geo | softmax |
| computer vision | image, video | detection | object-detection | cross-view-image-matching-for-geo | faster-r-cnn |
| computer vision | image, video | detection | object-detection | cross-view-image-matching-for-geo | rpn |
| computer vision | image, video | detection | object-detection | object-detection-via-aspect-ratio-and-context | rpn |
| computer vision | image, video | detection | object-detection | object-detection-via-aspect-ratio-and-context | r-fcn |
| computer vision | image, video | detection | object-detection | object-detection-via-aspect-ratio-and-context | roi-pooling |
| computer vision | image, video | detection | object-detection | object-detection-via-aspect-ratio-and-context | convolution |
| computer vision | image, video | detection | object-detection | object-detection-via-aspect-ratio-and-context | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | object-detection-via-aspect-ratio-and-context | softmax |
| computer vision | image, video | detection | object-detection | object-detection-via-aspect-ratio-and-context | faster-r-cnn |
| computer vision | image, video | detection | object-detection | improving-training-of-deep-neural-networks | batch-normalization |
| computer vision | image, video | detection | object-detection | vote3deep-fast-object-detection-in-3d-point | sparse-convolutions |
| computer vision | image, video | detection | object-detection | vote3deep-fast-object-detection-in-3d-point | feature-centric-voting |
| computer vision | image, video | detection | object-detection | vote3deep-fast-object-detection-in-3d-point | relu |
| computer vision | image, video | detection | object-detection | vote3deep-fast-object-detection-in-3d-point | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | vote3deep-fast-object-detection-in-3d-point | l1-regularization |
| computer vision | image, video | detection | object-detection | improving-object-detection-with-region | softmax |
| computer vision | image, video | detection | object-detection | improving-object-detection-with-region | ohem |
| computer vision | image, video | detection | object-detection | pixel-wise-ear-detection-with-convolutional | segnet |
| computer vision | image, video | detection | object-detection | pixel-wise-ear-detection-with-convolutional | relu |
| computer vision | image, video | detection | object-detection | pixel-wise-ear-detection-with-convolutional | he-initialization |
| computer vision | image, video | detection | object-detection | pixel-wise-ear-detection-with-convolutional | batch-normalization |
| computer vision | image, video | detection | object-detection | pixel-wise-ear-detection-with-convolutional | softmax |
| computer vision | image, video | detection | object-detection | pixel-wise-ear-detection-with-convolutional | convolution |
| computer vision | image, video | detection | object-detection | pixel-wise-ear-detection-with-convolutional | max-pooling |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | softmax |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | weight-decay |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | darknet-19 |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | randomresizedcrop |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | colorjitter |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | step-decay |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | polynomial-rate-decay |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | yolov2 |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | fast-yolov2 |
| computer vision | image, video | detection | object-detection | yolo9000-better-faster-stronger | ssd |
| computer vision | image, video | detection | object-detection | action-driven-object-detection-with-top-down | roi-pooling |
| computer vision | image, video | detection | object-detection | action-driven-object-detection-with-top-down | convolution |
| computer vision | image, video | detection | object-detection | action-driven-object-detection-with-top-down | softmax |
| computer vision | image, video | detection | object-detection | action-driven-object-detection-with-top-down | faster-r-cnn |
| computer vision | image, video | detection | object-detection | action-driven-object-detection-with-top-down | rpn |
| computer vision | image, video | detection | object-detection | geometric-deep-learning-on-graphs-and | monet |
| computer vision | image, video | detection | object-detection | learning-to-segment-object-candidates-via | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | learning-to-segment-object-candidates-via | deepmask |
| computer vision | image, video | detection | object-detection | learning-to-segment-object-candidates-via | dense-connections |
| computer vision | image, video | detection | object-detection | learning-to-segment-object-candidates-via | convolution |
| computer vision | image, video | detection | object-detection | learning-to-segment-object-candidates-via | softmax |
| computer vision | image, video | detection | object-detection | learning-to-segment-object-candidates-via | max-pooling |
| computer vision | image, video | detection | object-detection | learning-to-segment-object-candidates-via | vgg |
| computer vision | image, video | detection | object-detection | learning-to-segment-object-candidates-via | weight-decay |
| computer vision | image, video | detection | object-detection | learning-to-segment-object-candidates-via | 1x1-convolution |
| computer vision | image, video | detection | object-detection | learning-to-segment-object-candidates-via | relu |
| computer vision | image, video | detection | object-detection | learning-to-segment-object-candidates-via | dropout |
| computer vision | image, video | detection | object-detection | resfeats-residual-network-based-features-for | pca |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | googlenet |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | average-pooling |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | dense-connections |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | inception-module |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | softmax |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | local-response-normalization |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | convolution |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | max-pooling |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | 1x1-convolution |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | relu |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | dropout |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-of-mid-level | auxiliary-classifier |
| computer vision | image, video | detection | object-detection | backtracking-spatial-pyramid-pooling-spp | svm |
| computer vision | image, video | detection | object-detection | revisiting-batch-normalization-for-practical | batch-normalization |
| computer vision | image, video | detection | object-detection | crafting-gbd-net-for-object-detection | convolution |
| computer vision | image, video | detection | object-detection | pvanet-deep-but-lightweight-neural-networks | relu |
| computer vision | image, video | detection | object-detection | multiview-rgb-d-dataset-for-object-instance | dense-connections |
| computer vision | image, video | detection | object-detection | multiview-rgb-d-dataset-for-object-instance | alexnet |
| computer vision | image, video | detection | object-detection | multiview-rgb-d-dataset-for-object-instance | softmax |
| computer vision | image, video | detection | object-detection | multiview-rgb-d-dataset-for-object-instance | local-response-normalization |
| computer vision | image, video | detection | object-detection | multiview-rgb-d-dataset-for-object-instance | convolution |
| computer vision | image, video | detection | object-detection | multiview-rgb-d-dataset-for-object-instance | max-pooling |
| computer vision | image, video | detection | object-detection | multiview-rgb-d-dataset-for-object-instance | 1x1-convolution |
| computer vision | image, video | detection | object-detection | multiview-rgb-d-dataset-for-object-instance | relu |
| computer vision | image, video | detection | object-detection | multiview-rgb-d-dataset-for-object-instance | dropout |
| computer vision | image, video | detection | object-detection | multiview-rgb-d-dataset-for-object-instance | grouped-convolution |
| computer vision | image, video | detection | object-detection | using-filter-banks-in-convolutional-neural | convolution |
| computer vision | image, video | detection | object-detection | on-the-usability-of-deep-networks-for-object | convolution |
| computer vision | image, video | detection | object-detection | on-the-usability-of-deep-networks-for-object | fcn |
| computer vision | image, video | detection | object-detection | on-the-usability-of-deep-networks-for-object | max-pooling |
| computer vision | image, video | detection | object-detection | fully-convolutional-siamese-networks-for-1 | siamese-network |
| computer vision | image, video | detection | object-detection | face-detection-with-end-to-end-integration-of | softmax |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | resnet |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | rpn |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | average-pooling |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | global-average-pooling |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | roi-pooling |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | faster-r-cnn |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | convolution |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | residual-block |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | softmax |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | max-pooling |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | 1x1-convolution |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | relu |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | he-initialization |
| computer vision | image, video | detection | object-detection | object-detection-networks-on-convolutional | batch-normalization |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | selective-search |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | deepmask |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | dense-connections |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | roi-pooling |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | convolution |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | softmax |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | max-pooling |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | vgg |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | 1x1-convolution |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | relu |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | dropout |
| computer vision | image, video | detection | object-detection | a-multipath-network-for-object-detection | fast-r-cnn |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | dcnn |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | dense-connections |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | alexnet |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | k-means-clustering |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | vgg-16 |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | softmax |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | local-response-normalization |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | convolution |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | max-pooling |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | 1x1-convolution |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | relu |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | dropout |
| computer vision | image, video | detection | object-detection | intra-layer-nonuniform-quantization-for-deep | grouped-convolution |
| computer vision | image, video | detection | object-detection | is-faster-r-cnn-doing-well-for-pedestrian | roi-pooling |
| computer vision | image, video | detection | object-detection | is-faster-r-cnn-doing-well-for-pedestrian | convolution |
| computer vision | image, video | detection | object-detection | is-faster-r-cnn-doing-well-for-pedestrian | softmax |
| computer vision | image, video | detection | object-detection | is-faster-r-cnn-doing-well-for-pedestrian | faster-r-cnn |
| computer vision | image, video | detection | object-detection | is-faster-r-cnn-doing-well-for-pedestrian | rpn |
| computer vision | image, video | detection | object-detection | image-captioning-with-deep-bidirectional | tanh-activation |
| computer vision | image, video | detection | object-detection | image-captioning-with-deep-bidirectional | lstm |
| computer vision | image, video | detection | object-detection | image-captioning-with-deep-bidirectional | sigmoid-activation |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | average-pooling |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | global-average-pooling |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | convolution |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | residual-block |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | max-pooling |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | 1x1-convolution |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | r-fcn |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | relu |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | he-initialization |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | batch-normalization |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | residual-connection |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | r-fcn-object-detection-via-region-based-fully | resnet |
| computer vision | image, video | detection | reasoning | znni-maximizing-the-inference-throughput-of | convolution |
| computer vision | image, video | detection | object-detection | face-detection-with-the-faster-r-cnn | roi-pooling |
| computer vision | image, video | detection | object-detection | face-detection-with-the-faster-r-cnn | convolution |
| computer vision | image, video | detection | object-detection | face-detection-with-the-faster-r-cnn | softmax |
| computer vision | image, video | detection | object-detection | face-detection-with-the-faster-r-cnn | faster-r-cnn |
| computer vision | image, video | detection | object-detection | face-detection-with-the-faster-r-cnn | rpn |
| computer vision | image, video | detection | object-detection | re-ranking-object-proposals-for-object | svm |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | softmax |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | convolution |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | max-pooling |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | 1x1-convolution |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | relu |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | dropout |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | step-decay |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | randomresizedcrop |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | leaky-relu |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | dense-connections |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | yolov1 |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | roi-pooling |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | vgg |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | fast-r-cnn |
| computer vision | image, video | detection | object-detection | you-only-look-once-unified-real-time-object | colorjitter |
| computer vision | image, video | detection | object-detection | instance-search | roi-pooling |
| computer vision | image, video | detection | object-detection | instance-search | softmax |
| computer vision | image, video | detection | object-detection | instance-search | convolution |
| computer vision | image, video | detection | object-detection | instance-search | faster-r-cnn |
| computer vision | image, video | detection | object-detection | instance-search | rpn |
| computer vision | image, video | detection | object-detection | faster-r-cnn-features-for-instance-search | roi-pooling |
| computer vision | image, video | detection | object-detection | faster-r-cnn-features-for-instance-search | softmax |
| computer vision | image, video | detection | object-detection | faster-r-cnn-features-for-instance-search | convolution |
| computer vision | image, video | detection | object-detection | faster-r-cnn-features-for-instance-search | faster-r-cnn |
| computer vision | image, video | detection | object-detection | faster-r-cnn-features-for-instance-search | rpn |
| computer vision | image, video | detection | object-detection | recovering-6d-object-pose-and-predicting-next | autoencoder |
| computer vision | image, video | detection | object-detection | recovering-6d-object-pose-and-predicting-next | sparse-autoencoder |
| computer vision | image, video | detection | object-detection | object-detection-from-video-tubelets-with | convolution |
| computer vision | image, video | detection | object-detection | deep-feature-based-contextual-model-for | roi-pooling |
| computer vision | image, video | detection | object-detection | deep-feature-based-contextual-model-for | softmax |
| computer vision | image, video | detection | object-detection | deep-feature-based-contextual-model-for | convolution |
| computer vision | image, video | detection | object-detection | deep-feature-based-contextual-model-for | faster-r-cnn |
| computer vision | image, video | detection | object-detection | deep-feature-based-contextual-model-for | rpn |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | googlenet |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | average-pooling |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | dense-connections |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | inception-module |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | softmax |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | local-response-normalization |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | convolution |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | max-pooling |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | 1x1-convolution |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | relu |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | dropout |
| computer vision | image, video | detection | object-detection | factors-in-finetuning-deep-model-for-object | auxiliary-classifier |
| computer vision | image, video | detection | object-detection | training-region-based-object-detectors-with | ohem |
| computer vision | image, video | detection | object-detection | craft-objects-from-images | r-cnn |
| computer vision | image, video | detection | object-detection | craft-objects-from-images | convolution |
| computer vision | image, video | detection | object-detection | craft-objects-from-images | max-pooling |
| computer vision | image, video | detection | object-detection | craft-objects-from-images | svm |
| computer vision | image, video | detection | object-detection | adaptive-object-detection-using-adjacency-and | roi-pooling |
| computer vision | image, video | detection | object-detection | adaptive-object-detection-using-adjacency-and | convolution |
| computer vision | image, video | detection | object-detection | adaptive-object-detection-using-adjacency-and | softmax |
| computer vision | image, video | detection | object-detection | adaptive-object-detection-using-adjacency-and | faster-r-cnn |
| computer vision | image, video | detection | object-detection | adaptive-object-detection-using-adjacency-and | rpn |
| computer vision | image, video | detection | object-detection | learning-hough-regression-models-via-bridge | linear-regression |
| computer vision | image, video | detection | object-detection | an-end-to-end-convolutional-selective | autoencoder |
| computer vision | image, video | detection | object-detection | attentive-contexts-for-object-detection | convolution |
| computer vision | image, video | detection | object-detection | deep-sliding-shapes-for-amodal-3d-object | rpn |
| computer vision | image, video | detection | object-detection | deep-contrast-learning-for-salient-object | crf |
| computer vision | image, video | detection | object-detection | deepm-a-deep-part-based-model-for-object | r-cnn |
| computer vision | image, video | detection | object-detection | deepm-a-deep-part-based-model-for-object | convolution |
| computer vision | image, video | detection | object-detection | deepm-a-deep-part-based-model-for-object | max-pooling |
| computer vision | image, video | detection | object-detection | deepm-a-deep-part-based-model-for-object | svm |
| computer vision | image, video | detection | object-detection | faster-r-cnn-towards-real-time-object | rpn |
| computer vision | image, video | detection | object-detection | faster-r-cnn-towards-real-time-object | fast-r-cnn |
| computer vision | image, video | detection | object-detection | faster-r-cnn-towards-real-time-object | roi-pooling |
| computer vision | image, video | detection | object-detection | faster-r-cnn-towards-real-time-object | vgg-16 |
| computer vision | image, video | detection | object-detection | faster-r-cnn-towards-real-time-object | convolution |
| computer vision | image, video | detection | object-detection | faster-r-cnn-towards-real-time-object | softmax |
| computer vision | image, video | detection | object-detection | faster-r-cnn-towards-real-time-object | faster-r-cnn |
| computer vision | image, video | detection | object-detection | instance-aware-semantic-segmentation-via | roiwarp |
| computer vision | image, video | detection | object-detection | instance-aware-semantic-segmentation-via | vgg-16 |
| computer vision | image, video | detection | object-detection | instance-aware-semantic-segmentation-via | convolution |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | convolution |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | residual-block |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | max-pooling |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | weight-decay |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | 1x1-convolution |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | relu |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | he-initialization |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | batch-normalization |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | step-decay |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | randomresizedcrop |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | resnet |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | average-pooling |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | global-average-pooling |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | residual-connection |
| computer vision | image, video | detection | object-detection | deep-residual-learning-for-image-recognition | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | evaluation-of-object-detection-proposals | selective-search |
| computer vision | image, video | detection | object-detection | accelerating-very-deep-convolutional-networks | fast-r-cnn |
| computer vision | image, video | detection | object-detection | accelerating-very-deep-convolutional-networks | roi-pooling |
| computer vision | image, video | detection | object-detection | accelerating-very-deep-convolutional-networks | vgg-16 |
| computer vision | image, video | detection | object-detection | accelerating-very-deep-convolutional-networks | convolution |
| computer vision | image, video | detection | object-detection | accelerating-very-deep-convolutional-networks | softmax |
| computer vision | image, video | detection | object-detection | efficient-object-detection-for-high | dense-connections |
| computer vision | image, video | detection | object-detection | efficient-object-detection-for-high | alexnet |
| computer vision | image, video | detection | object-detection | efficient-object-detection-for-high | softmax |
| computer vision | image, video | detection | object-detection | efficient-object-detection-for-high | local-response-normalization |
| computer vision | image, video | detection | object-detection | efficient-object-detection-for-high | convolution |
| computer vision | image, video | detection | object-detection | efficient-object-detection-for-high | max-pooling |
| computer vision | image, video | detection | object-detection | efficient-object-detection-for-high | 1x1-convolution |
| computer vision | image, video | detection | object-detection | efficient-object-detection-for-high | relu |
| computer vision | image, video | detection | object-detection | efficient-object-detection-for-high | dropout |
| computer vision | image, video | detection | object-detection | efficient-object-detection-for-high | grouped-convolution |
| computer vision | image, video | detection | object-detection | relaxed-multiple-instance-svm-with | svm |
| computer vision | image, video | detection | object-detection | fast-r-cnn | fast-r-cnn |
| computer vision | image, video | detection | object-detection | fast-r-cnn | roi-pooling |
| computer vision | image, video | detection | object-detection | fast-r-cnn | convolution |
| computer vision | image, video | detection | object-detection | fast-r-cnn | softmax |
| computer vision | image, video | detection | object-detection | weakly-supervised-learning-for-salient-object | svm |
| computer vision | image, video | detection | object-detection | what-is-holding-back-convnets-for-detection | r-cnn |
| computer vision | image, video | detection | object-detection | what-is-holding-back-convnets-for-detection | convolution |
| computer vision | image, video | detection | object-detection | what-is-holding-back-convnets-for-detection | max-pooling |
| computer vision | image, video | detection | object-detection | what-is-holding-back-convnets-for-detection | svm |
| computer vision | image, video | detection | object-detection | lcnn-low-level-feature-embedded-cnn-for | svm |
| computer vision | image, video | detection | object-detection | what-makes-for-effective-detection-proposals | svm |
| computer vision | image, video | detection | object-detection | what-makes-for-effective-detection-proposals | fast-r-cnn |
| computer vision | image, video | detection | object-detection | what-makes-for-effective-detection-proposals | roi-pooling |
| computer vision | image, video | detection | object-detection | what-makes-for-effective-detection-proposals | r-cnn |
| computer vision | image, video | detection | object-detection | what-makes-for-effective-detection-proposals | convolution |
| computer vision | image, video | detection | object-detection | what-makes-for-effective-detection-proposals | softmax |
| computer vision | image, video | detection | object-detection | what-makes-for-effective-detection-proposals | max-pooling |
| computer vision | image, video | detection | object-detection | deep-cnn-ensemble-with-data-augmentation-for | r-cnn |
| computer vision | image, video | detection | object-detection | deep-cnn-ensemble-with-data-augmentation-for | convolution |
| computer vision | image, video | detection | object-detection | deep-cnn-ensemble-with-data-augmentation-for | max-pooling |
| computer vision | image, video | detection | object-detection | deep-cnn-ensemble-with-data-augmentation-for | svm |
| computer vision | image, video | detection | object-detection | r-cnn-minus-r | r-cnn |
| computer vision | image, video | detection | object-detection | r-cnn-minus-r | convolution |
| computer vision | image, video | detection | object-detection | r-cnn-minus-r | max-pooling |
| computer vision | image, video | detection | object-detection | r-cnn-minus-r | svm |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | googlenet |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | average-pooling |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | dense-connections |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | inception-module |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | softmax |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | local-response-normalization |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | convolution |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | max-pooling |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | 1x1-convolution |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | relu |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | dropout |
| computer vision | image, video | detection | object-detection | deepid-net-deformable-deep-convolutional | auxiliary-classifier |
| computer vision | image, video | detection | object-detection | joint-calibration-of-ensemble-of-exemplar | svm |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | dense-connections |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | spp-net |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | alexnet |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | zfnet |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | local-contrast-normalization |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | r-cnn |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | svm |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | grouped-convolution |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | sgd |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | convolution |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | overfeat |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | softmax |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | local-response-normalization |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | max-pooling |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | 1x1-convolution |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | spatial-pyramid-pooling |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | relu |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | dropout |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | randomresizedcrop |
| computer vision | image, video | detection | object-detection | spatial-pyramid-pooling-in-deep-convolutional | step-decay |
| computer vision | image, video | detection | object-detection | boosting-convolutional-features-for-robust | selective-search |
| computer vision | image, video | detection | object-detection | segdeepm-exploiting-segmentation-and-context | r-cnn |
| computer vision | image, video | detection | object-detection | segdeepm-exploiting-segmentation-and-context | convolution |
| computer vision | image, video | detection | object-detection | segdeepm-exploiting-segmentation-and-context | max-pooling |
| computer vision | image, video | detection | object-detection | segdeepm-exploiting-segmentation-and-context | svm |
| computer vision | image, video | detection | object-detection | compressing-deep-convolutional-networks-using | k-means-clustering |
| computer vision | image, video | detection | object-detection | highly-efficient-forward-and-backward | convolution |
| computer vision | image, video | detection | object-detection | untangling-local-and-global-deformations-in | convolution |
| computer vision | image, video | detection | object-detection | rich-feature-hierarchies-for-accurate-object | r-cnn |
| computer vision | image, video | detection | object-detection | rich-feature-hierarchies-for-accurate-object | convolution |
| computer vision | image, video | detection | object-detection | rich-feature-hierarchies-for-accurate-object | max-pooling |
| computer vision | image, video | detection | object-detection | rich-feature-hierarchies-for-accurate-object | svm |
| computer vision | image, video | detection | object-detection | deep-learning-representation-using | autoencoder |
| computer vision | image, video | detection | object-detection | hierarchical-adaptive-structural-svm-for | svm |
| computer vision | image, video | detection | object-detection | latent-fisher-discriminant-analysis | lda |
| computer vision | image, video | detection | object-detection | semantic-image-retrieval-by-uniting-deep | yolov2 |
| computer vision | image, video | detection | object-detection | semantic-image-retrieval-by-uniting-deep | average-pooling |
| computer vision | image, video | detection | object-detection | semantic-image-retrieval-by-uniting-deep | global-average-pooling |
| computer vision | image, video | detection | object-detection | semantic-image-retrieval-by-uniting-deep | convolution |
| computer vision | image, video | detection | object-detection | semantic-image-retrieval-by-uniting-deep | softmax |
| computer vision | image, video | detection | object-detection | semantic-image-retrieval-by-uniting-deep | max-pooling |
| computer vision | image, video | detection | object-detection | semantic-image-retrieval-by-uniting-deep | darknet-19 |
| computer vision | image, video | detection | object-detection | semantic-image-retrieval-by-uniting-deep | 1x1-convolution |
| computer vision | image, video | detection | object-detection | semantic-image-retrieval-by-uniting-deep | batch-normalization |
| computer vision | image, video | detection | object-detection | finding-original-image-of-a-sub-image-using | k-nn |
| computer vision | image, video | detection | object-detection | cfenet-an-accurate-and-efficient-single-shot | convolution |
| computer vision | image, video | detection | object-detection | cfenet-an-accurate-and-efficient-single-shot | ssd |
| computer vision | image, video | detection | object-detection | cfenet-an-accurate-and-efficient-single-shot | 1x1-convolution |
| computer vision | image, video | detection | object-detection | cfenet-an-accurate-and-efficient-single-shot | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | liver-lesion-detection-from-weakly-labeled | ran |
| computer vision | image, video | detection | object-detection | metaanchor-learning-to-detect-objects-with | fpn |
| computer vision | image, video | detection | object-detection | metaanchor-learning-to-detect-objects-with | convolution |
| computer vision | image, video | detection | object-detection | metaanchor-learning-to-detect-objects-with | focal-loss |
| computer vision | image, video | detection | object-detection | metaanchor-learning-to-detect-objects-with | 1x1-convolution |
| computer vision | image, video | detection | object-detection | metaanchor-learning-to-detect-objects-with | retinanet |
| computer vision | image, video | detection | object-detection | vehicle-image-generation-going-well-with-the | colorization |
| computer vision | image, video | detection | object-detection | auto-context-r-cnn | roi-align |
| computer vision | image, video | detection | object-detection | towards-multi-class-object-detection-in | convolution |
| computer vision | image, video | detection | object-detection | assessing-fish-abundance-from-underwater | roi-pooling |
| computer vision | image, video | detection | object-detection | assessing-fish-abundance-from-underwater | convolution |
| computer vision | image, video | detection | object-detection | assessing-fish-abundance-from-underwater | softmax |
| computer vision | image, video | detection | object-detection | assessing-fish-abundance-from-underwater | faster-r-cnn |
| computer vision | image, video | detection | object-detection | assessing-fish-abundance-from-underwater | rpn |
| computer vision | image, video | detection | object-detection | spatio-temporal-structured-sparse-regression | gaussian-process |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | global-average-pooling |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | softmax |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | convolution |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | max-pooling |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | 1x1-convolution |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | fire-module |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | relu |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | dropout |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | xavier-initialization |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | residual-connection |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | squeezenet |
| computer vision | image, video | detection | object-detection | pointseg-real-time-semantic-segmentation | average-pooling |
| computer vision | image, video | detection | object-detection | deep-adaptive-proposal-network-for-object | roi-pooling |
| computer vision | image, video | detection | object-detection | deep-adaptive-proposal-network-for-object | convolution |
| computer vision | image, video | detection | object-detection | deep-adaptive-proposal-network-for-object | softmax |
| computer vision | image, video | detection | object-detection | deep-adaptive-proposal-network-for-object | faster-r-cnn |
| computer vision | image, video | detection | object-detection | deep-adaptive-proposal-network-for-object | rpn |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | 1x1-convolution |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | relu |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | he-initialization |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | batch-normalization |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | resnet |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | deeplab |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | dilated-convolution |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | crf |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | average-pooling |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | dense-connections |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | global-average-pooling |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | residual-connection |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | feedforward-network |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | convolution |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | residual-block |
| computer vision | image, video | detection | object-detection | in-pixels-we-trust-from-pixel-labeling-to | max-pooling |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | yolov2 |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | rpn |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | average-pooling |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | global-average-pooling |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | roi-pooling |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | convolution |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | softmax |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | faster-r-cnn |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | max-pooling |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | darknet-19 |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | 1x1-convolution |
| computer vision | image, video | detection | object-detection | physical-adversarial-examples-for-object | batch-normalization |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | average-pooling |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | lstm |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | mnasnet |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | dense-connections |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | global-average-pooling |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | depthwise-separable-convolution |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | rmsprop |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | depthwise-convolution |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | tanh-activation |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | sigmoid-activation |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | linear-warmup-with-linear-decay |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | squeeze-and-excitation-block |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | pointwise-convolution |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | convolution |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | softmax |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | weight-decay |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | 1x1-convolution |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | relu |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | inverted-residual-block |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | dropout |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | batch-normalization |
| computer vision | image, video | detection | object-detection | mnasnet-platform-aware-neural-architecture | randomresizedcrop |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | hourglass-module |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | cornernet |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | stacked-hourglass-network |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | colorjitter |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | residual-connection |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | corner-pooling |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | convolution |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | focal-loss |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | max-pooling |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | 1x1-convolution |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | adam |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | relu |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | randomresizedcrop |
| computer vision | image, video | detection | object-detection | cornernet-detecting-objects-as-paired | step-decay |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | global-average-pooling |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | convolution |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | residual-block |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | max-pooling |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | 1x1-convolution |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | relu |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | he-initialization |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | batch-normalization |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | residual-connection |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | resnet |
| computer vision | image, video | detection | object-detection | network-decoupling-from-regular-to-depthwise | average-pooling |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | global-average-pooling |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | softmax |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | convolution |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | max-pooling |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | 1x1-convolution |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | fire-module |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | relu |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | dropout |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | xavier-initialization |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | residual-connection |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | squeezenet |
| computer vision | image, video | detection | object-detection | dnn-feature-map-compression-using-learned | average-pooling |
| computer vision | image, video | detection | object-detection | fast-and-accurate-convolutional-neural | fpn |
| computer vision | image, video | detection | object-detection | fast-and-accurate-convolutional-neural | convolution |
| computer vision | image, video | detection | object-detection | fast-and-accurate-convolutional-neural | focal-loss |
| computer vision | image, video | detection | object-detection | fast-and-accurate-convolutional-neural | 1x1-convolution |
| computer vision | image, video | detection | object-detection | fast-and-accurate-convolutional-neural | retinanet |
| computer vision | image, video | detection | object-detection | a-survey-of-modern-object-detection | roi-pooling |
| computer vision | image, video | detection | object-detection | a-survey-of-modern-object-detection | convolution |
| computer vision | image, video | detection | object-detection | a-survey-of-modern-object-detection | softmax |
| computer vision | image, video | detection | object-detection | a-survey-of-modern-object-detection | faster-r-cnn |
| computer vision | image, video | detection | object-detection | a-survey-of-modern-object-detection | rpn |
| computer vision | image, video | detection | object-detection | fingertip-detection-and-tracking-for | roi-pooling |
| computer vision | image, video | detection | object-detection | fingertip-detection-and-tracking-for | convolution |
| computer vision | image, video | detection | object-detection | fingertip-detection-and-tracking-for | softmax |
| computer vision | image, video | detection | object-detection | fingertip-detection-and-tracking-for | faster-r-cnn |
| computer vision | image, video | detection | object-detection | fingertip-detection-and-tracking-for | rpn |
| computer vision | image, video | detection | object-detection | temporal-spatial-mapping-for-action | temporal-attention |
| computer vision | image, video | detection | object-detection | focal-loss-in-3d-object-detection | focal-loss |
| computer vision | image, video | detection | object-detection | revisit-multinomial-logistic-regression-in | softmax |
| computer vision | image, video | detection | object-detection | revisit-multinomial-logistic-regression-in | logistic-regression |
| computer vision | image, video | detection | object-detection | revisit-multinomial-logistic-regression-in | linear-layer |
| computer vision | image, video | detection | object-detection | evaluating-merging-strategies-for-sampling | dropout |
| computer vision | image, video | detection | object-detection | an-fpga-accelerated-design-for-deep-learning | convolution |
| computer vision | image, video | detection | object-detection | an-fpga-accelerated-design-for-deep-learning | ssd |
| computer vision | image, video | detection | object-detection | an-fpga-accelerated-design-for-deep-learning | 1x1-convolution |
| computer vision | image, video | detection | object-detection | an-fpga-accelerated-design-for-deep-learning | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | cadp-a-novel-dataset-for-cctv-traffic-camera | tanh-activation |
| computer vision | image, video | detection | object-detection | cadp-a-novel-dataset-for-cctv-traffic-camera | lstm |
| computer vision | image, video | detection | object-detection | cadp-a-novel-dataset-for-cctv-traffic-camera | rpn |
| computer vision | image, video | detection | object-detection | cadp-a-novel-dataset-for-cctv-traffic-camera | sigmoid-activation |
| computer vision | image, video | detection | object-detection | cadp-a-novel-dataset-for-cctv-traffic-camera | roi-pooling |
| computer vision | image, video | detection | object-detection | cadp-a-novel-dataset-for-cctv-traffic-camera | convolution |
| computer vision | image, video | detection | object-detection | cadp-a-novel-dataset-for-cctv-traffic-camera | softmax |
| computer vision | image, video | detection | object-detection | cadp-a-novel-dataset-for-cctv-traffic-camera | faster-r-cnn |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | 1x1-convolution |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | relu |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | he-initialization |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | batch-normalization |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | mask-r-cnn |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | resnet |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | rpn |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | average-pooling |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | global-average-pooling |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | roi-pooling |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | faster-r-cnn |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | residual-connection |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | roi-align |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | vgg-16 |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | convolution |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | softmax |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | residual-block |
| computer vision | image, video | detection | object-detection | softer-nms-rethinking-bounding-box-regression | max-pooling |
| computer vision | image, video | detection | object-detection | global-weighted-average-pooling-bridges-pixel | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | global-weighted-average-pooling-bridges-pixel | convolution |
| computer vision | image, video | detection | object-detection | global-weighted-average-pooling-bridges-pixel | max-pooling |
| computer vision | image, video | detection | object-detection | global-weighted-average-pooling-bridges-pixel | average-pooling |
| computer vision | image, video | detection | object-detection | global-weighted-average-pooling-bridges-pixel | r-fcn |
| computer vision | image, video | detection | object-detection | object-detection-from-scratch-with-deep | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | object-detection-from-scratch-with-deep | fpn |
| computer vision | image, video | detection | object-detection | object-detection-from-scratch-with-deep | convolution |
| computer vision | image, video | detection | object-detection | object-detection-from-scratch-with-deep | ssd |
| computer vision | image, video | detection | object-detection | object-detection-from-scratch-with-deep | 1x1-convolution |
| computer vision | image, video | detection | object-detection | object-detection-from-scratch-with-deep | dense-connections |
| computer vision | image, video | detection | object-detection | satellite-imagery-multiscale-rapid-detection | ssd |
| computer vision | image, video | detection | object-detection | satellite-imagery-multiscale-rapid-detection | rpn |
| computer vision | image, video | detection | object-detection | satellite-imagery-multiscale-rapid-detection | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | satellite-imagery-multiscale-rapid-detection | roi-pooling |
| computer vision | image, video | detection | object-detection | satellite-imagery-multiscale-rapid-detection | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | satellite-imagery-multiscale-rapid-detection | convolution |
| computer vision | image, video | detection | object-detection | satellite-imagery-multiscale-rapid-detection | softmax |
| computer vision | image, video | detection | object-detection | satellite-imagery-multiscale-rapid-detection | faster-r-cnn |
| computer vision | image, video | detection | object-detection | satellite-imagery-multiscale-rapid-detection | 1x1-convolution |
| computer vision | image, video | detection | object-detection | satellite-imagery-multiscale-rapid-detection | r-fcn |
| computer vision | image, video | detection | object-detection | dropout-distillation-for-efficiently | dropout |
| computer vision | image, video | detection | object-detection | dropout-distillation-for-efficiently | roi-pooling |
| computer vision | image, video | detection | object-detection | dropout-distillation-for-efficiently | convolution |
| computer vision | image, video | detection | object-detection | dropout-distillation-for-efficiently | softmax |
| computer vision | image, video | detection | object-detection | dropout-distillation-for-efficiently | faster-r-cnn |
| computer vision | image, video | detection | object-detection | dropout-distillation-for-efficiently | rpn |
| computer vision | image, video | detection | object-detection | real-time-dynamic-object-detection-for | carla |
| computer vision | image, video | detection | object-detection | boundary-guided-feature-aggregation-network | convolution |
| computer vision | image, video | detection | object-detection | boundary-guided-feature-aggregation-network | fcn |
| computer vision | image, video | detection | object-detection | boundary-guided-feature-aggregation-network | max-pooling |
| computer vision | image, video | detection | object-detection | landmine-detection-using-autoencoders-on | autoencoder |
| computer vision | image, video | detection | object-detection | catdet-cascaded-tracked-detector-for | roi-pooling |
| computer vision | image, video | detection | object-detection | catdet-cascaded-tracked-detector-for | convolution |
| computer vision | image, video | detection | object-detection | catdet-cascaded-tracked-detector-for | softmax |
| computer vision | image, video | detection | object-detection | catdet-cascaded-tracked-detector-for | faster-r-cnn |
| computer vision | image, video | detection | object-detection | catdet-cascaded-tracked-detector-for | rpn |
| computer vision | image, video | detection | object-detection | pixel-and-feature-level-based-domain-adaption | cycle-consistency-loss |
| computer vision | image, video | detection | object-detection | multi-view-x-ray-r-cnn | roi-pooling |
| computer vision | image, video | detection | object-detection | multi-view-x-ray-r-cnn | softmax |
| computer vision | image, video | detection | object-detection | multi-view-x-ray-r-cnn | convolution |
| computer vision | image, video | detection | object-detection | multi-view-x-ray-r-cnn | faster-r-cnn |
| computer vision | image, video | detection | object-detection | multi-view-x-ray-r-cnn | rpn |
| computer vision | image, video | detection | object-detection | ktan-knowledge-transfer-adversarial-network | softmax |
| computer vision | image, video | detection | object-detection | ktan-knowledge-transfer-adversarial-network | knowledge-distillation |
| computer vision | image, video | reasoning | knowledge representation and reasoning | ktan-knowledge-transfer-adversarial-network | softmax |
| computer vision | image, video | reasoning | knowledge representation and reasoning | ktan-knowledge-transfer-adversarial-network | knowledge-distillation |
| computer vision | image, video | detection | object-detection | salience-biased-loss-for-object-detection-in | fpn |
| computer vision | image, video | detection | object-detection | salience-biased-loss-for-object-detection-in | convolution |
| computer vision | image, video | detection | object-detection | salience-biased-loss-for-object-detection-in | focal-loss |
| computer vision | image, video | detection | object-detection | salience-biased-loss-for-object-detection-in | 1x1-convolution |
| computer vision | image, video | detection | object-detection | salience-biased-loss-for-object-detection-in | retinanet |
| computer vision | image, video | detection | object-detection | query-based-logo-segmentation | convolution |
| computer vision | image, video | detection | object-detection | query-based-logo-segmentation | 1x1-convolution |
| computer vision | image, video | detection | object-detection | roarnet-a-robust-3d-object-detection-based-on | pointnet |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | sfam |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | ssd |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | convolution |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | residual-block |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | max-pooling |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | focal-loss |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | relu |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | retinanet |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | he-initialization |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | batch-normalization |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | tum |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | step-decay |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | mlfpn |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | fpn |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | ffmv1 |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | average-pooling |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | dense-connections |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | linear-warmup |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | global-average-pooling |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | ffmv2 |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | residual-connection |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | sigmoid-activation |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | roi-align |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | softmax |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | weight-decay |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | 1x1-convolution |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | dropout |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | mask-r-cnn |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | resnet |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | m2det |
| computer vision | image, video | detection | object-detection | m2det-a-single-shot-object-detector-based-on | vgg |
| computer vision | image, video | detection | object-detection | ban-focusing-on-boundary-context-for-object | convolution |
| computer vision | image, video | detection | object-detection | yolo-lite-a-real-time-object-detection | convolution |
| computer vision | image, video | detection | object-detection | yolo-lite-a-real-time-object-detection | ssd |
| computer vision | image, video | detection | object-detection | yolo-lite-a-real-time-object-detection | 1x1-convolution |
| computer vision | image, video | detection | object-detection | yolo-lite-a-real-time-object-detection | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | derpn-taking-a-further-step-toward-more | rpn |
| computer vision | image, video | detection | object-detection | composite-binary-decomposition-networks | vgg-16 |
| computer vision | image, video | detection | object-detection | composite-binary-decomposition-networks | softmax |
| computer vision | image, video | detection | object-detection | composite-binary-decomposition-networks | convolution |
| computer vision | image, video | detection | object-detection | composite-binary-decomposition-networks | max-pooling |
| computer vision | image, video | detection | object-detection | composite-binary-decomposition-networks | segnet |
| computer vision | image, video | detection | object-detection | composite-binary-decomposition-networks | relu |
| computer vision | image, video | detection | object-detection | composite-binary-decomposition-networks | he-initialization |
| computer vision | image, video | detection | object-detection | composite-binary-decomposition-networks | batch-normalization |
| computer vision | image, video | detection | object-detection | fotonnet-a-hw-efficient-object-detection | dense-connections |
| computer vision | image, video | detection | object-detection | fotonnet-a-hw-efficient-object-detection | alexnet |
| computer vision | image, video | detection | object-detection | fotonnet-a-hw-efficient-object-detection | softmax |
| computer vision | image, video | detection | object-detection | fotonnet-a-hw-efficient-object-detection | local-response-normalization |
| computer vision | image, video | detection | object-detection | fotonnet-a-hw-efficient-object-detection | convolution |
| computer vision | image, video | detection | object-detection | fotonnet-a-hw-efficient-object-detection | max-pooling |
| computer vision | image, video | detection | object-detection | fotonnet-a-hw-efficient-object-detection | 1x1-convolution |
| computer vision | image, video | detection | object-detection | fotonnet-a-hw-efficient-object-detection | relu |
| computer vision | image, video | detection | object-detection | fotonnet-a-hw-efficient-object-detection | dropout |
| computer vision | image, video | detection | object-detection | fotonnet-a-hw-efficient-object-detection | grouped-convolution |
| computer vision | image, video | detection | object-detection | pixel-anchor-a-fast-oriented-scene-text | 1x1-convolution |
| computer vision | image, video | detection | object-detection | pixel-anchor-a-fast-oriented-scene-text | spatial-pyramid-pooling |
| computer vision | image, video | detection | object-detection | pixel-anchor-a-fast-oriented-scene-text | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | pixel-anchor-a-fast-oriented-scene-text | convolution |
| computer vision | image, video | detection | object-detection | pixel-anchor-a-fast-oriented-scene-text | ssd |
| computer vision | image, video | detection | object-detection | pixel-anchor-a-fast-oriented-scene-text | aspp |
| computer vision | image, video | detection | object-detection | pixel-anchor-a-fast-oriented-scene-text | dilated-convolution |
| computer vision | image, video | detection | object-detection | open-vocabulary-phrase-detection | roi-pooling |
| computer vision | image, video | detection | object-detection | open-vocabulary-phrase-detection | convolution |
| computer vision | image, video | detection | object-detection | open-vocabulary-phrase-detection | softmax |
| computer vision | image, video | detection | object-detection | open-vocabulary-phrase-detection | faster-r-cnn |
| computer vision | image, video | detection | object-detection | open-vocabulary-phrase-detection | rpn |
| computer vision | image, video | detection | object-detection | data-efficient-graph-embedding-learning-for | roi-pooling |
| computer vision | image, video | detection | object-detection | data-efficient-graph-embedding-learning-for | softmax |
| computer vision | image, video | detection | object-detection | data-efficient-graph-embedding-learning-for | convolution |
| computer vision | image, video | detection | object-detection | data-efficient-graph-embedding-learning-for | faster-r-cnn |
| computer vision | image, video | detection | object-detection | data-efficient-graph-embedding-learning-for | rpn |
| computer vision | image, video | detection | object-detection | data-efficient-graph-embedding-learning-for | pcb |
| computer vision | image, video | detection | object-detection | scalable-logo-recognition-using-proxies | triplet-loss |
| computer vision | image, video | detection | object-detection | retina-u-net-embarrassingly-simple | convolution |
| computer vision | image, video | detection | object-detection | retina-u-net-embarrassingly-simple | max-pooling |
| computer vision | image, video | detection | object-detection | retina-u-net-embarrassingly-simple | relu |
| computer vision | image, video | detection | object-detection | retina-u-net-embarrassingly-simple | u-net |
| computer vision | image, video | detection | object-detection | retina-u-net-embarrassingly-simple | concatenated-skip-connection |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | resnet |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | average-pooling |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | global-average-pooling |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | resnext-block |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | grouped-convolution |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | residual-connection |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | convolution |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | residual-block |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | max-pooling |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | 1x1-convolution |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | resnext |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | relu |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | he-initialization |
| computer vision | image, video | detection | object-detection | rethinking-imagenet-pre-training | batch-normalization |
| computer vision | image, video | detection | object-detection | a-proposal-based-solution-to-spatio-temporal | temporal-jittering |
| computer vision | image, video | detection | object-detection | defect-detection-from-uav-images-based-on | roi-pooling |
| computer vision | image, video | detection | object-detection | defect-detection-from-uav-images-based-on | convolution |
| computer vision | image, video | detection | object-detection | defect-detection-from-uav-images-based-on | softmax |
| computer vision | image, video | detection | object-detection | defect-detection-from-uav-images-based-on | faster-r-cnn |
| computer vision | image, video | detection | object-detection | defect-detection-from-uav-images-based-on | rpn |
| computer vision | image, video | detection | object-detection | distorting-neural-representations-to-generate | softmax |
| computer vision | image, video | detection | object-detection | leveraging-filter-correlations-for-deep-model | vgg-16 |
| computer vision | image, video | detection | object-detection | expandnets-exploiting-linear-redundancy-to | knowledge-distillation |
| computer vision | image, video | detection | object-detection | non-local-roi-for-cross-object-perception | rpn |
| computer vision | image, video | detection | object-detection | non-local-roi-for-cross-object-perception | roi-pooling |
| computer vision | image, video | detection | object-detection | non-local-roi-for-cross-object-perception | mask-r-cnn |
| computer vision | image, video | detection | object-detection | non-local-roi-for-cross-object-perception | roi-align |
| computer vision | image, video | detection | object-detection | non-local-roi-for-cross-object-perception | convolution |
| computer vision | image, video | detection | object-detection | non-local-roi-for-cross-object-perception | softmax |
| computer vision | image, video | detection | object-detection | non-local-roi-for-cross-object-perception | faster-r-cnn |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | relu |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | he-initialization |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | batch-normalization |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | deformable-roi-pooling |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | rpn |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | average-pooling |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | global-average-pooling |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | roi-pooling |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | faster-r-cnn |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | deformable-convolution |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | residual-connection |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | deformable-convnets |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | roi-align |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | softmax |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | weight-decay |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | 1x1-convolution |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | mask-r-cnn |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | resnet |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | convolution |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | residual-block |
| computer vision | image, video | detection | object-detection | deformable-convnets-v2-more-deformable-better | max-pooling |
| computer vision | image, video | detection | object-detection | fast-object-detection-in-compressed-video | convolution |
| computer vision | image, video | detection | object-detection | fast-object-detection-in-compressed-video | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | fast-object-detection-in-compressed-video | memory-network |
| computer vision | image, video | detection | object-detection | fast-object-detection-in-compressed-video | r-fcn |
| computer vision | image, video | detection | object-detection | probability-based-detection-quality-pdq-a | monte-carlo-dropout |
| computer vision | image, video | detection | object-detection | probability-based-detection-quality-pdq-a | dropout |
| computer vision | image, video | detection | object-detection | ccnet-criss-cross-attention-for-semantic | ccnet |
| computer vision | image, video | detection | object-detection | ccnet-criss-cross-attention-for-semantic | non-local-block |
| computer vision | image, video | detection | object-detection | ccnet-criss-cross-attention-for-semantic | residual-connection |
| computer vision | image, video | detection | object-detection | ccnet-criss-cross-attention-for-semantic | non-local-operation |
| computer vision | image, video | detection | object-detection | ccnet-criss-cross-attention-for-semantic | 1x1-convolution |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | espnet |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | dilated-convolution |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | average-pooling |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | dense-connections |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | global-average-pooling |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | residual-connection |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | sigmoid-activation |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | strided-eesp |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | pointwise-convolution |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | espnetv2 |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | softmax |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | 1x1-convolution |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | dropout |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | randomresizedcrop |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | esp |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | lstm |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | hierarchical-feature-fusion |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | concatenated-skip-connection |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | eesp |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | depthwise-separable-convolution |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | cyclical-learning-rate-policy |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | depthwise-convolution |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | grouped-convolution |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | tanh-activation |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | eru |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | sgd |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | prelu |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | convolution |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | depthwise-dilated-separable-convolution |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | groupwise-point-convolution |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | he-initialization |
| computer vision | image, video | detection | object-detection | espnetv2-a-light-weight-power-efficient-and | batch-normalization |
| computer vision | image, video | detection | object-detection | deep-regionlets-blended-representation-and | fpn |
| computer vision | image, video | detection | object-detection | deep-regionlets-blended-representation-and | mask-r-cnn |
| computer vision | image, video | detection | object-detection | deep-regionlets-blended-representation-and | roi-align |
| computer vision | image, video | detection | object-detection | deep-regionlets-blended-representation-and | convolution |
| computer vision | image, video | detection | object-detection | deep-regionlets-blended-representation-and | softmax |
| computer vision | image, video | detection | object-detection | deep-regionlets-blended-representation-and | focal-loss |
| computer vision | image, video | detection | object-detection | deep-regionlets-blended-representation-and | 1x1-convolution |
| computer vision | image, video | detection | object-detection | deep-regionlets-blended-representation-and | retinanet |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | global-average-pooling |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | convolution |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | residual-block |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | max-pooling |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | 1x1-convolution |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | relu |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | he-initialization |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | batch-normalization |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | residual-connection |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | resnet |
| computer vision | image, video | detection | object-detection | imagenet-trained-cnns-are-biased-towards | average-pooling |
| computer vision | image, video | detection | object-detection | grid-r-cnn | grid-r-cnn |
| computer vision | image, video | detection | object-detection | grid-r-cnn | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | grid-r-cnn | convolution |
| computer vision | image, video | detection | object-detection | grid-r-cnn | residual-block |
| computer vision | image, video | detection | object-detection | grid-r-cnn | max-pooling |
| computer vision | image, video | detection | object-detection | grid-r-cnn | resnext |
| computer vision | image, video | detection | object-detection | grid-r-cnn | relu |
| computer vision | image, video | detection | object-detection | grid-r-cnn | he-initialization |
| computer vision | image, video | detection | object-detection | grid-r-cnn | batch-normalization |
| computer vision | image, video | detection | object-detection | grid-r-cnn | syncbn |
| computer vision | image, video | detection | object-detection | grid-r-cnn | fpn |
| computer vision | image, video | detection | object-detection | grid-r-cnn | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | grid-r-cnn | dilated-convolution |
| computer vision | image, video | detection | object-detection | grid-r-cnn | rpn |
| computer vision | image, video | detection | object-detection | grid-r-cnn | average-pooling |
| computer vision | image, video | detection | object-detection | grid-r-cnn | global-average-pooling |
| computer vision | image, video | detection | object-detection | grid-r-cnn | roi-pooling |
| computer vision | image, video | detection | object-detection | grid-r-cnn | faster-r-cnn |
| computer vision | image, video | detection | object-detection | grid-r-cnn | residual-connection |
| computer vision | image, video | detection | object-detection | grid-r-cnn | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | grid-r-cnn | sigmoid-activation |
| computer vision | image, video | detection | object-detection | grid-r-cnn | roi-align |
| computer vision | image, video | detection | object-detection | grid-r-cnn | softmax |
| computer vision | image, video | detection | object-detection | grid-r-cnn | fcn |
| computer vision | image, video | detection | object-detection | grid-r-cnn | weight-decay |
| computer vision | image, video | detection | object-detection | grid-r-cnn | 1x1-convolution |
| computer vision | image, video | detection | object-detection | grid-r-cnn | resnet |
| computer vision | image, video | detection | object-detection | grid-r-cnn | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | grid-r-cnn | resnext-block |
| computer vision | image, video | detection | object-detection | grid-r-cnn | grouped-convolution |
| computer vision | image, video | detection | object-detection | transferable-adversarial-attacks-for-image | convolution |
| computer vision | image, video | detection | object-detection | transferable-adversarial-attacks-for-image | ssd |
| computer vision | image, video | detection | object-detection | transferable-adversarial-attacks-for-image | 1x1-convolution |
| computer vision | image, video | detection | object-detection | transferable-adversarial-attacks-for-image | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | residual-connection |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | layer-normalization |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | dense-connections |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | label-smoothing |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | transformer |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | scaled |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | softmax |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | position-wise-feed-forward-layer |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | multi-head-attention |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | adam |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | relu |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | absolute-position-encodings |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | dropout |
| computer vision | image, video | detection | object-detection | learning-roi-transformer-for-detecting | bpe |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | nesterov-accelerated-gradient |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | mixup |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | average-pooling |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | cosine-annealing |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | label-smoothing |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | global-average-pooling |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | residual-connection |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | resnet-d |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | convolution |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | residual-block |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | max-pooling |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | weight-decay |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | 1x1-convolution |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | relu |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | randomresizedcrop |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | xavier-initialization |
| computer vision | image, video | detection | object-detection | bag-of-tricks-for-image-classification-with | batch-normalization |
| computer vision | image, video | detection | object-detection | iterative-reorganization-with-weak-spatial | jigsaw |
| computer vision | image, video | detection | object-detection | sada-semantic-adversarial-diagnostic-attacks | gan |
| computer vision | image, video | detection | object-detection | sada-semantic-adversarial-diagnostic-attacks | carla |
| computer vision | image, video | detection | object-detection | feature-matters-a-stage-by-stage-approach-for | knowledge-distillation |
| computer vision | image, video | detection | object-detection | omnia-faster-r-cnn-detection-in-the-wild | roi-pooling |
| computer vision | image, video | detection | object-detection | omnia-faster-r-cnn-detection-in-the-wild | convolution |
| computer vision | image, video | detection | object-detection | omnia-faster-r-cnn-detection-in-the-wild | softmax |
| computer vision | image, video | detection | object-detection | omnia-faster-r-cnn-detection-in-the-wild | faster-r-cnn |
| computer vision | image, video | detection | object-detection | omnia-faster-r-cnn-detection-in-the-wild | rpn |
| computer vision | image, video | detection | object-detection | super-resolution | convolution |
| computer vision | image, video | detection | object-detection | super-resolution | ssd |
| computer vision | image, video | detection | object-detection | super-resolution | 1x1-convolution |
| computer vision | image, video | detection | object-detection | super-resolution | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | the-effects-of-super-resolution-on-object | convolution |
| computer vision | image, video | detection | object-detection | the-effects-of-super-resolution-on-object | ssd |
| computer vision | image, video | detection | object-detection | the-effects-of-super-resolution-on-object | 1x1-convolution |
| computer vision | image, video | detection | object-detection | the-effects-of-super-resolution-on-object | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | picanet-pixel-wise-contextual-attention | convolution |
| computer vision | image, video | detection | object-detection | picanet-pixel-wise-contextual-attention | max-pooling |
| computer vision | image, video | detection | object-detection | picanet-pixel-wise-contextual-attention | relu |
| computer vision | image, video | detection | object-detection | picanet-pixel-wise-contextual-attention | u-net |
| computer vision | image, video | detection | object-detection | picanet-pixel-wise-contextual-attention | concatenated-skip-connection |
| computer vision | image, video | detection | object-detection | cnn-based-multi-instance-multi-task-learning | max-pooling |
| computer vision | image, video | detection | object-detection | squantizer-simultaneous-learning-for-both | tanh-activation |
| computer vision | image, video | detection | object-detection | squantizer-simultaneous-learning-for-both | softmax |
| computer vision | image, video | detection | object-detection | squantizer-simultaneous-learning-for-both | lstm |
| computer vision | image, video | detection | object-detection | squantizer-simultaneous-learning-for-both | sigmoid-activation |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | resnet |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | average-pooling |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | dense-connections |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | global-average-pooling |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | mobilenetv1 |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | channel-shuffle |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | depthwise-separable-convolution |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | depthwise-convolution |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | grouped-convolution |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | residual-connection |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | pointwise-convolution |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | softmax |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | convolution |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | residual-block |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | shufflenet |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | max-pooling |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | shufflenet-block |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | 1x1-convolution |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | mobilenetv2 |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | relu |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | groupwise-point-convolution |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | he-initialization |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | inverted-residual-block |
| computer vision | image, video | detection | object-detection | slimmable-neural-networks | batch-normalization |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | global-average-pooling |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | convolution |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | residual-block |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | max-pooling |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | group-normalization |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | 1x1-convolution |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | relu |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | he-initialization |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | batch-normalization |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | residual-connection |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | resnet |
| computer vision | image, video | detection | object-detection | kalman-normalization-normalizing-internal | average-pooling |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | global-average-pooling |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | convolution |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | residual-block |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | max-pooling |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | 1x1-convolution |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | relu |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | he-initialization |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | batch-normalization |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | residual-connection |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | resnet |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | ssd |
| computer vision | image, video | detection | object-detection | revisiting-multi-task-learning-with-rock-a | average-pooling |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | convolution |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | softmax |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | max-pooling |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | weight-decay |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | 1x1-convolution |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | relu |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | batch-normalization |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | step-decay |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | average-pooling |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | two-way-dense-layer |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | dense-connections |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | cosine-annealing |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | global-average-pooling |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | peleenet |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | residual-connection |
| computer vision | image, video | detection | object-detection | pelee-a-real-time-object-detection-system-on-1 | ssd |
| computer vision | image, video | detection | object-detection | fast-template-evaluation-with-vector | svm |
| computer vision | image, video | detection | object-detection | flow-guided-recurrent-neural-encoder-for | tanh-activation |
| computer vision | image, video | detection | object-detection | flow-guided-recurrent-neural-encoder-for | convolution |
| computer vision | image, video | detection | object-detection | flow-guided-recurrent-neural-encoder-for | fcn |
| computer vision | image, video | detection | object-detection | flow-guided-recurrent-neural-encoder-for | max-pooling |
| computer vision | image, video | detection | object-detection | flow-guided-recurrent-neural-encoder-for | lstm |
| computer vision | image, video | detection | object-detection | flow-guided-recurrent-neural-encoder-for | sigmoid-activation |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | global-average-pooling |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | convolution |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | residual-block |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | max-pooling |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | npid |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | 1x1-convolution |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | relu |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | he-initialization |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | batch-normalization |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | residual-connection |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | resnet |
| computer vision | image, video | detection | object-detection | unsupervised-feature-learning-via-non-1 | average-pooling |
| computer vision | image, video | detection | object-detection | generative-adversarial-learning-towards-fast | convolution |
| computer vision | image, video | detection | object-detection | generative-adversarial-learning-towards-fast | ssd |
| computer vision | image, video | detection | object-detection | generative-adversarial-learning-towards-fast | 1x1-convolution |
| computer vision | image, video | detection | object-detection | generative-adversarial-learning-towards-fast | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | learning-globally-optimized-object-detector | reinforce |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | googlenet |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | average-pooling |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | dense-connections |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | alexnet |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | inception-module |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | softmax |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | local-response-normalization |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | convolution |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | max-pooling |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | 1x1-convolution |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | relu |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | dropout |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | grouped-convolution |
| computer vision | image, video | detection | object-detection | clip-q-deep-network-compression-learning-by | auxiliary-classifier |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | fpn |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | dilated-convolution |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | dilated-bottleneck-with-projection-block |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | average-pooling |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | rpn |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | global-average-pooling |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | dilated-bottleneck-block |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | roi-pooling |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | faster-r-cnn |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | residual-connection |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | detnet |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | ssd |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | convolution |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | softmax |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | focal-loss |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | 1x1-convolution |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | r-fcn |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | retinanet |
| computer vision | image, video | detection | object-detection | detnet-design-backbone-for-object-detection | relu |
| computer vision | image, video | detection | object-detection | parallel-feature-pyramid-network-for-object | spatial-pyramid-pooling |
| computer vision | image, video | detection | object-detection | pyramid-dilated-deeper-convlstm-for-video | tanh-activation |
| computer vision | image, video | detection | object-detection | pyramid-dilated-deeper-convlstm-for-video | convolution |
| computer vision | image, video | detection | object-detection | pyramid-dilated-deeper-convlstm-for-video | dilated-convolution |
| computer vision | image, video | detection | object-detection | pyramid-dilated-deeper-convlstm-for-video | sigmoid-activation |
| computer vision | image, video | detection | object-detection | pyramid-dilated-deeper-convlstm-for-video | convlstm |
| computer vision | image, video | detection | object-detection | tbn-convolutional-neural-network-with-ternary | dense-connections |
| computer vision | image, video | detection | object-detection | tbn-convolutional-neural-network-with-ternary | alexnet |
| computer vision | image, video | detection | object-detection | tbn-convolutional-neural-network-with-ternary | softmax |
| computer vision | image, video | detection | object-detection | tbn-convolutional-neural-network-with-ternary | local-response-normalization |
| computer vision | image, video | detection | object-detection | tbn-convolutional-neural-network-with-ternary | convolution |
| computer vision | image, video | detection | object-detection | tbn-convolutional-neural-network-with-ternary | max-pooling |
| computer vision | image, video | detection | object-detection | tbn-convolutional-neural-network-with-ternary | 1x1-convolution |
| computer vision | image, video | detection | object-detection | tbn-convolutional-neural-network-with-ternary | relu |
| computer vision | image, video | detection | object-detection | tbn-convolutional-neural-network-with-ternary | dropout |
| computer vision | image, video | detection | object-detection | tbn-convolutional-neural-network-with-ternary | grouped-convolution |
| computer vision | image, video | detection | object-detection | region-proposal-networks-with-contextual | rpn |
| computer vision | image, video | detection | object-detection | studying-the-plasticity-in-deep-convolutional | vgg-16 |
| computer vision | image, video | detection | object-detection | studying-the-plasticity-in-deep-convolutional | softmax |
| computer vision | image, video | detection | object-detection | studying-the-plasticity-in-deep-convolutional | convolution |
| computer vision | image, video | detection | object-detection | studying-the-plasticity-in-deep-convolutional | max-pooling |
| computer vision | image, video | detection | object-detection | studying-the-plasticity-in-deep-convolutional | segnet |
| computer vision | image, video | detection | object-detection | studying-the-plasticity-in-deep-convolutional | relu |
| computer vision | image, video | detection | object-detection | studying-the-plasticity-in-deep-convolutional | he-initialization |
| computer vision | image, video | detection | object-detection | studying-the-plasticity-in-deep-convolutional | batch-normalization |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | resnet |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | dilated-convolution |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | average-pooling |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | global-average-pooling |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | deformable-convolution |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | residual-connection |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | soft-nms |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | tridentnet-block |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | convolution |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | residual-block |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | max-pooling |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | tridentnet |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | 1x1-convolution |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | relu |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | he-initialization |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | batch-normalization |
| computer vision | image, video | detection | object-detection | scale-aware-trident-networks-for-object | step-decay |
| computer vision | image, video | detection | object-detection | 3d-object-detection-using-scale-invariant-and | average-pooling |
| computer vision | image, video | detection | object-detection | 3d-object-detection-using-scale-invariant-and | sigmoid-activation |
| computer vision | image, video | detection | object-detection | 3d-object-detection-using-scale-invariant-and | dense-connections |
| computer vision | image, video | detection | object-detection | 3d-object-detection-using-scale-invariant-and | squeeze-and-excitation-block |
| computer vision | image, video | detection | object-detection | 3d-object-detection-using-scale-invariant-and | senet |
| computer vision | image, video | detection | object-detection | 3d-object-detection-using-scale-invariant-and | global-average-pooling |
| computer vision | image, video | detection | object-detection | 3d-object-detection-using-scale-invariant-and | convolution |
| computer vision | image, video | detection | object-detection | 3d-object-detection-using-scale-invariant-and | softmax |
| computer vision | image, video | detection | object-detection | 3d-object-detection-using-scale-invariant-and | max-pooling |
| computer vision | image, video | detection | object-detection | 3d-object-detection-using-scale-invariant-and | relu |
| computer vision | image, video | detection | object-detection | 3d-object-detection-using-scale-invariant-and | he-initialization |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | guided-anchoring |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | convolution |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | softmax |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | residual-block |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | max-pooling |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | focal-loss |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | 1x1-convolution |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | relu |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | retinanet |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | he-initialization |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | batch-normalization |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | fpn |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | resnet |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | rpn |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | average-pooling |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | global-average-pooling |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | roi-pooling |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | faster-r-cnn |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | fast-r-cnn |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | region-proposal-by-guided-anchoring | residual-connection |
| computer vision | image, video | detection | object-detection | a-survey-of-the-recent-architectures-of-deep | tanh-activation |
| computer vision | image, video | detection | object-detection | a-survey-of-the-recent-architectures-of-deep | mish |
| computer vision | image, video | detection | object-detection | a-survey-of-the-recent-architectures-of-deep | softplus |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | resnext |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | relu |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | he-initialization |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | batch-normalization |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | fpn |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | global-convolutional-network |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | average-pooling |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | rpn |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | dense-connections |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | global-average-pooling |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | senet |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | deformable-convolution |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | residual-connection |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | soft-nms |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | sigmoid-activation |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | bottom-up-path-augmentation |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | squeeze-and-excitation-block |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | htc |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | roi-align |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | softmax |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | cascade-r-cnn |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | 1x1-convolution |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | resnet |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | pafpn |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | precise-roi-pooling |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | cascade-mask-r-cnn |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | resnext-block |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | grouped-convolution |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | convolution |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | residual-block |
| computer vision | image, video | detection | object-detection | hybrid-task-cascade-for-instance-segmentation | max-pooling |
| computer vision | image, video | detection | object-detection | consistent-optimization-for-single-shot | fpn |
| computer vision | image, video | detection | object-detection | consistent-optimization-for-single-shot | convolution |
| computer vision | image, video | detection | object-detection | consistent-optimization-for-single-shot | focal-loss |
| computer vision | image, video | detection | object-detection | consistent-optimization-for-single-shot | 1x1-convolution |
| computer vision | image, video | detection | object-detection | consistent-optimization-for-single-shot | retinanet |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | corner-pooling |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | convolution |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | residual-block |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | max-pooling |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | dextr |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | 1x1-convolution |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | adam |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | relu |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | he-initialization |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | randomresizedcrop |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | batch-normalization |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | extremenet |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | random-scaling |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | resnet |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | dilated-convolution |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | average-pooling |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | global-average-pooling |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | hourglass-module |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | cornernet |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | stacked-hourglass-network |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | colorjitter |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | residual-connection |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | soft-nms |
| computer vision | image, video | detection | object-detection | bottom-up-object-detection-by-grouping | pyramid-pooling-module |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | googlenet |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | average-pooling |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | dense-connections |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | alexnet |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | inception-module |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | lenet |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | vgg |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | grouped-convolution |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | auxiliary-classifier |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | admm |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | softmax |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | local-response-normalization |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | convolution |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | max-pooling |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | 1x1-convolution |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | relu |
| computer vision | image, video | detection | object-detection | towards-compact-convnets-via-structure | dropout |
| computer vision | image, video | detection | object-detection | superpixels | crf |
| computer vision | image, video | detection | object-detection | superpixels | svm |
| computer vision | image, video | detection | object-detection | superpixels | selective-search |
| computer vision | image, video | detection | object-detection | superpixels | googlenet |
| computer vision | image, video | detection | object-detection | superpixels | average-pooling |
| computer vision | image, video | detection | object-detection | superpixels | dense-connections |
| computer vision | image, video | detection | object-detection | superpixels | inception-module |
| computer vision | image, video | detection | object-detection | superpixels | softmax |
| computer vision | image, video | detection | object-detection | superpixels | local-response-normalization |
| computer vision | image, video | detection | object-detection | superpixels | convolution |
| computer vision | image, video | detection | object-detection | superpixels | max-pooling |
| computer vision | image, video | detection | object-detection | superpixels | svm |
| computer vision | image, video | detection | object-detection | superpixels | 1x1-convolution |
| computer vision | image, video | detection | object-detection | superpixels | relu |
| computer vision | image, video | detection | object-detection | superpixels | dropout |
| computer vision | image, video | detection | object-detection | superpixels | auxiliary-classifier |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | googlenet |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | average-pooling |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | dense-connections |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | inception-module |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | softmax |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | local-response-normalization |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | convolution |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | max-pooling |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | svm |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | 1x1-convolution |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | relu |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | dropout |
| computer vision | image, video | detection | object-detection | object-detection-by-labeling-superpixels | auxiliary-classifier |
| computer vision | image, video | detection | object-detection | progressively-parsing-interactional-objects | tanh-activation |
| computer vision | image, video | detection | object-detection | progressively-parsing-interactional-objects | lstm |
| computer vision | image, video | detection | object-detection | progressively-parsing-interactional-objects | sigmoid-activation |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | googlenet |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | lstm |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | average-pooling |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | dense-connections |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | inception-module |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | auxiliary-classifier |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | tanh-activation |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | sigmoid-activation |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | softmax |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | local-response-normalization |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | convolution |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | max-pooling |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | 1x1-convolution |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | relu |
| computer vision | image, video | detection | object-detection | weighted-entropy-based-quantization-for-deep | dropout |
| computer vision | image, video | detection | object-detection | robust-visual-tracking-using-oblique-random | svm |
| computer vision | image, video | detection | object-detection | unsupervised-tube-extraction-using | selective-search |
| computer vision | image, video | detection | object-detection | scenenet-rgb-d-can-5m-synthetic-images-beat | vgg-16 |
| computer vision | image, video | segmentation | sementic segmentation | patchfcn-for-intracranial-hemorrhage | convolution |
| computer vision | image, video | segmentation | sementic segmentation | patchfcn-for-intracranial-hemorrhage | fcn |
| computer vision | image, video | segmentation | sementic segmentation | patchfcn-for-intracranial-hemorrhage | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | sbnet-sparse-blocks-network-for-fast | convolution |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | convolution |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | relu |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | resnet |
| computer vision | image, video | segmentation | sementic segmentation | resnet-sparsifier-learning-strict-identity | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | algorithms-for-semantic-segmentation-of | dcnn |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | non-maximum-suppression |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | roi-align |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | convolution |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | softmax |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | weight-decay |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | relu |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | step-decay |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | fpn |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | sgd-with-momentum |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | dilated-convolution |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | dilated-bottleneck-with-projection-block |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | rpn |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | randomhorizontalflip |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | dilated-bottleneck-block |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | roi-pooling |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | faster-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | detnet-a-backbone-network-for-object | detnet |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | deeplabv3 |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | dilated-convolution |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | relu6 |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | rmsprop |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | depthwise-separable-convolution |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | aspp |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | depthwise-convolution |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | pointwise-convolution |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | convolution |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | weight-decay |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | mobilenetv2 |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | relu |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | spatial-pyramid-pooling |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | inverted-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | dropout |
| computer vision | image, video | segmentation | sementic segmentation | mobilenetv2-inverted-residuals-and-linear | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | pose2seg-detection-free-human-instance | roi-align |
| computer vision | image, video | segmentation | sementic segmentation | pose2seg-detection-free-human-instance | convolution |
| computer vision | image, video | segmentation | sementic segmentation | pose2seg-detection-free-human-instance | softmax |
| computer vision | image, video | segmentation | sementic segmentation | deeply-supervised-salient-object-detection | convolution |
| computer vision | image, video | segmentation | sementic segmentation | deeply-supervised-salient-object-detection | fcn |
| computer vision | image, video | segmentation | sementic segmentation | deeply-supervised-salient-object-detection | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | resnext-block |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | grouped-convolution |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | adaptive-feature-pooling |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | bottom-up-path-augmentation |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | roi-align |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | convolution |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | weight-decay |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | resnext |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | relu |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | panet |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | sgd-with-momentum |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | fpn |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | resnet |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | pafpn |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | rpn |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | dense-connections |
| computer vision | image, video | segmentation | sementic segmentation | path-aggregation-network-for-instance | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deep-6dpose-recovering-6d-object-pose-from-a | mask-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | deep-6dpose-recovering-6d-object-pose-from-a | roi-align |
| computer vision | image, video | segmentation | sementic segmentation | deep-6dpose-recovering-6d-object-pose-from-a | convolution |
| computer vision | image, video | segmentation | sementic segmentation | deep-6dpose-recovering-6d-object-pose-from-a | softmax |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | roi-align |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | convolution |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | softmax |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | resnext |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | relu |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | mask-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | resnet |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | resnext-block |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | grouped-convolution |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | mask-r-cnn | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | convolution |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | relu |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | resnet |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | dilated-convolution |
| computer vision | image, video | segmentation | sementic segmentation | masklab-instance-segmentation-by-refining | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | squeeze-segnet-a-new-fast-deep-convolutional | segnet |
| computer vision | image, video | segmentation | sementic segmentation | squeeze-segnet-a-new-fast-deep-convolutional | relu |
| computer vision | image, video | segmentation | sementic segmentation | squeeze-segnet-a-new-fast-deep-convolutional | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | squeeze-segnet-a-new-fast-deep-convolutional | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | squeeze-segnet-a-new-fast-deep-convolutional | softmax |
| computer vision | image, video | segmentation | sementic segmentation | squeeze-segnet-a-new-fast-deep-convolutional | convolution |
| computer vision | image, video | segmentation | sementic segmentation | squeeze-segnet-a-new-fast-deep-convolutional | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | gaussian-filter-in-crf-based-semantic | convolution |
| computer vision | image, video | segmentation | sementic segmentation | gaussian-filter-in-crf-based-semantic | fcn |
| computer vision | image, video | segmentation | sementic segmentation | gaussian-filter-in-crf-based-semantic | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | gaussian-filter-in-crf-based-semantic | crf |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | relu |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | fpn |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | resnet |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | rpn |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | roi-pooling |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | faster-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | ssd |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | non-maximum-suppression |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | convolution |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | softmax |
| computer vision | image, video | segmentation | sementic segmentation | chainercv-a-library-for-deep-learning-in | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | learning-to-segment-on-tiny-datasets-a-new | crf |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | convolution |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | softmax |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | weight-decay |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | relu |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | xavier-initialization |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | step-decay |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | sgd-with-momentum |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | resnet |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | rpn |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | roi-pooling |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | faster-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | rmsprop |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | revisiting-unreasonable-effectiveness-of-data | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | relu |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | deformable-roi-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | resnet |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | deformable-position-sensitive-roi-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | deformable-convolution |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | deformable-convnets |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | convolution |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convolutional-networks | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | pixelwise-instance-segmentation-with-a | crf |
| computer vision | image, video | segmentation | sementic segmentation | resfeats-residual-network-based-features-for | pca |
| computer vision | image, video | segmentation | sementic segmentation | higher-order-conditional-random-fields-in | crf |
| computer vision | image, video | reasoning | sementic segmentation | znni-maximizing-the-inference-throughput-of | convolution |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | sgd-with-momentum |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | deeplab |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | feedforward-network |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | crf |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | dense-connections |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | softmax |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | convolution |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | vgg |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | weight-decay |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | relu |
| computer vision | image, video | segmentation | sementic segmentation | semantic-image-segmentation-with-deep | dropout |
| computer vision | image, video | segmentation | sementic segmentation | re-ranking-object-proposals-for-object | svm |
| computer vision | image, video | segmentation | sementic segmentation | object-detection-from-video-tubelets-with | convolution |
| computer vision | image, video | segmentation | sementic segmentation | instance-aware-semantic-segmentation-via | roiwarp |
| computer vision | image, video | segmentation | sementic segmentation | instance-aware-semantic-segmentation-via | vgg-16 |
| computer vision | image, video | segmentation | sementic segmentation | instance-aware-semantic-segmentation-via | convolution |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | convolution |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | weight-decay |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | relu |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | step-decay |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | randomresizedcrop |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | sgd-with-momentum |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | resnet |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | randomhorizontalflip |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | deep-residual-learning-for-image-recognition | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | segdeepm-exploiting-segmentation-and-context | r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | segdeepm-exploiting-segmentation-and-context | convolution |
| computer vision | image, video | segmentation | sementic segmentation | segdeepm-exploiting-segmentation-and-context | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | segdeepm-exploiting-segmentation-and-context | svm |
| computer vision | image, video | segmentation | sementic segmentation | highly-efficient-forward-and-backward | convolution |
| computer vision | image, video | segmentation | sementic segmentation | rich-feature-hierarchies-for-accurate-object | r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | rich-feature-hierarchies-for-accurate-object | convolution |
| computer vision | image, video | segmentation | sementic segmentation | rich-feature-hierarchies-for-accurate-object | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | rich-feature-hierarchies-for-accurate-object | svm |
| computer vision | image, video | segmentation | sementic segmentation | vehicle-image-generation-going-well-with-the | colorization |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | softmax |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | convolution |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | fire-module |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | relu |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | dropout |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | xavier-initialization |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | squeezenet |
| computer vision | image, video | segmentation | sementic segmentation | pointseg-real-time-semantic-segmentation | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | relu |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | resnet |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | deeplab |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | dilated-convolution |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | crf |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | dense-connections |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | feedforward-network |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | convolution |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | in-pixels-we-trust-from-pixel-labeling-to | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | evaluating-merging-strategies-for-sampling | dropout |
| computer vision | image, video | segmentation | sementic segmentation | boundary-guided-feature-aggregation-network | convolution |
| computer vision | image, video | segmentation | sementic segmentation | boundary-guided-feature-aggregation-network | fcn |
| computer vision | image, video | segmentation | sementic segmentation | boundary-guided-feature-aggregation-network | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | composite-binary-decomposition-networks | vgg-16 |
| computer vision | image, video | segmentation | sementic segmentation | composite-binary-decomposition-networks | softmax |
| computer vision | image, video | segmentation | sementic segmentation | composite-binary-decomposition-networks | convolution |
| computer vision | image, video | segmentation | sementic segmentation | composite-binary-decomposition-networks | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | composite-binary-decomposition-networks | segnet |
| computer vision | image, video | segmentation | sementic segmentation | composite-binary-decomposition-networks | relu |
| computer vision | image, video | segmentation | sementic segmentation | composite-binary-decomposition-networks | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | composite-binary-decomposition-networks | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | pixel-anchor-a-fast-oriented-scene-text | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | pixel-anchor-a-fast-oriented-scene-text | spatial-pyramid-pooling |
| computer vision | image, video | segmentation | sementic segmentation | pixel-anchor-a-fast-oriented-scene-text | non-maximum-suppression |
| computer vision | image, video | segmentation | sementic segmentation | pixel-anchor-a-fast-oriented-scene-text | convolution |
| computer vision | image, video | segmentation | sementic segmentation | pixel-anchor-a-fast-oriented-scene-text | ssd |
| computer vision | image, video | segmentation | sementic segmentation | pixel-anchor-a-fast-oriented-scene-text | aspp |
| computer vision | image, video | segmentation | sementic segmentation | pixel-anchor-a-fast-oriented-scene-text | dilated-convolution |
| computer vision | image, video | segmentation | sementic segmentation | retina-u-net-embarrassingly-simple | convolution |
| computer vision | image, video | segmentation | sementic segmentation | retina-u-net-embarrassingly-simple | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | retina-u-net-embarrassingly-simple | relu |
| computer vision | image, video | segmentation | sementic segmentation | retina-u-net-embarrassingly-simple | u-net |
| computer vision | image, video | segmentation | sementic segmentation | retina-u-net-embarrassingly-simple | concatenated-skip-connection |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | resnet |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | resnext-block |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | grouped-convolution |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | convolution |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | resnext |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | relu |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | rethinking-imagenet-pre-training | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | expandnets-exploiting-linear-redundancy-to | knowledge-distillation |
| computer vision | image, video | segmentation | sementic segmentation | non-local-roi-for-cross-object-perception | rpn |
| computer vision | image, video | segmentation | sementic segmentation | non-local-roi-for-cross-object-perception | roi-pooling |
| computer vision | image, video | segmentation | sementic segmentation | non-local-roi-for-cross-object-perception | mask-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | non-local-roi-for-cross-object-perception | roi-align |
| computer vision | image, video | segmentation | sementic segmentation | non-local-roi-for-cross-object-perception | convolution |
| computer vision | image, video | segmentation | sementic segmentation | non-local-roi-for-cross-object-perception | softmax |
| computer vision | image, video | segmentation | sementic segmentation | non-local-roi-for-cross-object-perception | faster-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | relu |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | deformable-roi-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | sgd-with-momentum |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | rpn |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | roi-pooling |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | faster-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | deformable-convolution |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | deformable-convnets |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | roi-align |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | softmax |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | weight-decay |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | mask-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | resnet |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | non-maximum-suppression |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | convolution |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | deformable-convnets-v2-more-deformable-better | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | ccnet-criss-cross-attention-for-semantic | ccnet |
| computer vision | image, video | segmentation | sementic segmentation | ccnet-criss-cross-attention-for-semantic | non-local-block |
| computer vision | image, video | segmentation | sementic segmentation | ccnet-criss-cross-attention-for-semantic | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | ccnet-criss-cross-attention-for-semantic | non-local-operation |
| computer vision | image, video | segmentation | sementic segmentation | ccnet-criss-cross-attention-for-semantic | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | espnet |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | dilated-convolution |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | dense-connections |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | sigmoid-activation |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | strided-eesp |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | pointwise-convolution |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | espnetv2 |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | softmax |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | dropout |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | randomresizedcrop |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | esp |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | lstm |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | hierarchical-feature-fusion |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | randomhorizontalflip |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | concatenated-skip-connection |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | eesp |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | depthwise-separable-convolution |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | cyclical-learning-rate-policy |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | depthwise-convolution |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | grouped-convolution |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | tanh-activation |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | eru |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | sgd |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | prelu |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | convolution |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | depthwise-dilated-separable-convolution |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | groupwise-point-convolution |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | espnetv2-a-light-weight-power-efficient-and | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | nesterov-accelerated-gradient |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | mixup |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | cosine-annealing |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | randomhorizontalflip |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | label-smoothing |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | resnet-d |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | convolution |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | weight-decay |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | relu |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | randomresizedcrop |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | xavier-initialization |
| computer vision | image, video | segmentation | sementic segmentation | bag-of-tricks-for-image-classification-with | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | iterative-reorganization-with-weak-spatial | jigsaw |
| computer vision | image, video | segmentation | sementic segmentation | picanet-pixel-wise-contextual-attention | convolution |
| computer vision | image, video | segmentation | sementic segmentation | picanet-pixel-wise-contextual-attention | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | picanet-pixel-wise-contextual-attention | relu |
| computer vision | image, video | segmentation | sementic segmentation | picanet-pixel-wise-contextual-attention | u-net |
| computer vision | image, video | segmentation | sementic segmentation | picanet-pixel-wise-contextual-attention | concatenated-skip-connection |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | resnet |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | dense-connections |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | mobilenetv1 |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | channel-shuffle |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | depthwise-separable-convolution |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | depthwise-convolution |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | grouped-convolution |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | pointwise-convolution |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | softmax |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | convolution |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | shufflenet |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | shufflenet-block |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | mobilenetv2 |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | relu |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | groupwise-point-convolution |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | inverted-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | slimmable-neural-networks | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | fpn |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | dilated-convolution |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | dilated-bottleneck-with-projection-block |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | rpn |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | dilated-bottleneck-block |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | roi-pooling |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | position-sensitive-roi-pooling |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | faster-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | detnet |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | ssd |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | non-maximum-suppression |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | convolution |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | softmax |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | focal-loss |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | r-fcn |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | retinanet |
| computer vision | image, video | segmentation | sementic segmentation | detnet-design-backbone-for-object-detection | relu |
| computer vision | image, video | segmentation | sementic segmentation | pyramid-dilated-deeper-convlstm-for-video | tanh-activation |
| computer vision | image, video | segmentation | sementic segmentation | pyramid-dilated-deeper-convlstm-for-video | convolution |
| computer vision | image, video | segmentation | sementic segmentation | pyramid-dilated-deeper-convlstm-for-video | dilated-convolution |
| computer vision | image, video | segmentation | sementic segmentation | pyramid-dilated-deeper-convlstm-for-video | sigmoid-activation |
| computer vision | image, video | segmentation | sementic segmentation | pyramid-dilated-deeper-convlstm-for-video | convlstm |
| computer vision | image, video | segmentation | sementic segmentation | studying-the-plasticity-in-deep-convolutional | vgg-16 |
| computer vision | image, video | segmentation | sementic segmentation | studying-the-plasticity-in-deep-convolutional | softmax |
| computer vision | image, video | segmentation | sementic segmentation | studying-the-plasticity-in-deep-convolutional | convolution |
| computer vision | image, video | segmentation | sementic segmentation | studying-the-plasticity-in-deep-convolutional | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | studying-the-plasticity-in-deep-convolutional | segnet |
| computer vision | image, video | segmentation | sementic segmentation | studying-the-plasticity-in-deep-convolutional | relu |
| computer vision | image, video | segmentation | sementic segmentation | studying-the-plasticity-in-deep-convolutional | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | studying-the-plasticity-in-deep-convolutional | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | resnext |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | relu |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | he-initialization |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | batch-normalization |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | fpn |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | global-convolutional-network |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | rpn |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | dense-connections |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | senet |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | deformable-convolution |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | bottleneck-residual-block |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | soft-nms |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | sigmoid-activation |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | bottom-up-path-augmentation |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | squeeze-and-excitation-block |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | htc |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | roi-align |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | softmax |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | cascade-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | resnet |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | pafpn |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | precise-roi-pooling |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | cascade-mask-r-cnn |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | resnext-block |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | convolution |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | residual-block |
| computer vision | image, video | segmentation | sementic segmentation | hybrid-task-cascade-for-instance-segmentation | max-pooling |
| computer vision | image, video | segmentation | sementic segmentation | scenenet-rgb-d-can-5m-synthetic-images-beat | vgg-16 |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | yolov2 |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | rpn |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | average-pooling |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | global-average-pooling |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | roi-pooling |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | convolution |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | softmax |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | faster-r-cnn |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | max-pooling |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | darknet-19 |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | 1x1-convolution |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | fast-r-cnn |
| computer vision | image, video | recognition | object recognition | model-based-active-learning-to-detect | batch-normalization |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | global-average-pooling |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | softmax |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | convolution |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | max-pooling |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | 1x1-convolution |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | fire-module |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | relu |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | dropout |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | xavier-initialization |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | residual-connection |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | squeezenet |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | dcnn |
| computer vision | image, video | recognition | object recognition | squeezejet-high-level-synthesis-accelerator | average-pooling |
| computer vision | image, video | recognition | object recognition | algorithms-for-semantic-segmentation-of | dcnn |
| computer vision | image, video | recognition | object recognition | deep-learning-object-detection-methods-for | roi-pooling |
| computer vision | image, video | recognition | object recognition | deep-learning-object-detection-methods-for | convolution |
| computer vision | image, video | recognition | object recognition | deep-learning-object-detection-methods-for | softmax |
| computer vision | image, video | recognition | object recognition | deep-learning-object-detection-methods-for | faster-r-cnn |
| computer vision | image, video | recognition | object recognition | deep-learning-object-detection-methods-for | rpn |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | googlenet |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | average-pooling |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | rpn |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | dense-connections |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | roi-pooling |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | inception-module |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | faster-r-cnn |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | vgg |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | auxiliary-classifier |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | fast-r-cnn |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | convolution |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | softmax |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | local-response-normalization |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | max-pooling |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | 1x1-convolution |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | relu |
| computer vision | image, video | recognition | object recognition | t-cnn-tubelets-with-convolutional-neural | dropout |
| computer vision | image, video | recognition | object recognition | temporal-dynamic-graph-lstm-for-action-driven | tanh-activation |
| computer vision | image, video | recognition | object recognition | temporal-dynamic-graph-lstm-for-action-driven | memory-network |
| computer vision | image, video | recognition | object recognition | temporal-dynamic-graph-lstm-for-action-driven | lstm |
| computer vision | image, video | recognition | object recognition | temporal-dynamic-graph-lstm-for-action-driven | sigmoid-activation |
| computer vision | image, video | recognition | object recognition | improving-robustness-of-feature | convolution |
| computer vision | image, video | recognition | object recognition | recurrent-soft-attention-model-for-common | tanh-activation |
| computer vision | image, video | recognition | object recognition | recurrent-soft-attention-model-for-common | lstm |
| computer vision | image, video | recognition | object recognition | recurrent-soft-attention-model-for-common | sigmoid-activation |
| computer vision | image, video | recognition | object recognition | deep-sliding-shapes-for-amodal-3d-object | rpn |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | dense-connections |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | spp-net |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | alexnet |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | randomhorizontalflip |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | zfnet |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | local-contrast-normalization |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | r-cnn |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | svm |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | grouped-convolution |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | sgd |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | convolution |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | overfeat |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | softmax |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | local-response-normalization |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | max-pooling |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | 1x1-convolution |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | spatial-pyramid-pooling |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | relu |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | dropout |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | randomresizedcrop |
| computer vision | image, video | recognition | object recognition | spatial-pyramid-pooling-in-deep-convolutional | step-decay |
| computer vision | image, video | recognition | object recognition | compressing-deep-convolutional-networks-using | k-means-clustering |
| computer vision | image, video | recognition | object recognition | distorting-neural-representations-to-generate | softmax |
| computer vision | image, video | recognition | object recognition | sbnet-sparse-blocks-network-for-fast | convolution |
| computer vision | image, video | recognition | object recognition | complex-yolo-real-time-3d-object-detection-on | yolov2 |
| computer vision | image, video | recognition | object recognition | complex-yolo-real-time-3d-object-detection-on | average-pooling |
| computer vision | image, video | recognition | object recognition | complex-yolo-real-time-3d-object-detection-on | global-average-pooling |
| computer vision | image, video | recognition | object recognition | complex-yolo-real-time-3d-object-detection-on | convolution |
| computer vision | image, video | recognition | object recognition | complex-yolo-real-time-3d-object-detection-on | softmax |
| computer vision | image, video | recognition | object recognition | complex-yolo-real-time-3d-object-detection-on | max-pooling |
| computer vision | image, video | recognition | object recognition | complex-yolo-real-time-3d-object-detection-on | darknet-19 |
| computer vision | image, video | recognition | object recognition | complex-yolo-real-time-3d-object-detection-on | 1x1-convolution |
| computer vision | image, video | recognition | object recognition | complex-yolo-real-time-3d-object-detection-on | batch-normalization |
| computer vision | image, video | recognition | object recognition | joint-3d-proposal-generation-and-object | rpn |
| computer vision | image, video | recognition | object recognition | accurate-single-stage-detector-using | rpn |
| computer vision | image, video | recognition | object recognition | accurate-single-stage-detector-using | dense-connections |
| computer vision | image, video | recognition | object recognition | accurate-single-stage-detector-using | roi-pooling |
| computer vision | image, video | recognition | object recognition | accurate-single-stage-detector-using | vgg-16 |
| computer vision | image, video | recognition | object recognition | accurate-single-stage-detector-using | convolution |
| computer vision | image, video | recognition | object recognition | accurate-single-stage-detector-using | softmax |
| computer vision | image, video | recognition | object recognition | accurate-single-stage-detector-using | max-pooling |
| computer vision | image, video | recognition | object recognition | accurate-single-stage-detector-using | vgg |
| computer vision | image, video | recognition | object recognition | accurate-single-stage-detector-using | faster-r-cnn |
| computer vision | image, video | recognition | object recognition | accurate-single-stage-detector-using | relu |
| computer vision | image, video | recognition | object recognition | accurate-single-stage-detector-using | dropout |
| computer vision | image, video | recognition | object recognition | vote3deep-fast-object-detection-in-3d-point | sparse-convolutions |
| computer vision | image, video | recognition | object recognition | vote3deep-fast-object-detection-in-3d-point | feature-centric-voting |
| computer vision | image, video | recognition | object recognition | vote3deep-fast-object-detection-in-3d-point | relu |
| computer vision | image, video | recognition | object recognition | vote3deep-fast-object-detection-in-3d-point | non-maximum-suppression |
| computer vision | image, video | recognition | object recognition | vote3deep-fast-object-detection-in-3d-point | l1-regularization |
| computer vision | image, video | recognition | object recognition | deep-sliding-shapes-for-amodal-3d-object | rpn |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | global-average-pooling |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | softmax |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | convolution |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | max-pooling |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | 1x1-convolution |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | fire-module |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | relu |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | dropout |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | xavier-initialization |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | residual-connection |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | squeezenet |
| computer vision | image, video | recognition | object recognition | pointseg-real-time-semantic-segmentation | average-pooling |
| computer vision | image, video | recognition | object recognition | focal-loss-in-3d-object-detection | focal-loss |
| computer vision | image, video | recognition | object recognition | roarnet-a-robust-3d-object-detection-based-on | pointnet |
| computer vision | image, video | recognition | 3d object recognition | 3d-object-detection-using-scale-invariant-and | average-pooling |
| computer vision | image, video | recognition | 3d object recognition | 3d-object-detection-using-scale-invariant-and | sigmoid-activation |
| computer vision | image, video | recognition | 3d object recognition | 3d-object-detection-using-scale-invariant-and | dense-connections |
| computer vision | image, video | recognition | 3d object recognition | 3d-object-detection-using-scale-invariant-and | squeeze-and-excitation-block |
| computer vision | image, video | recognition | 3d object recognition | 3d-object-detection-using-scale-invariant-and | senet |
| computer vision | image, video | recognition | 3d object recognition | 3d-object-detection-using-scale-invariant-and | global-average-pooling |
| computer vision | image, video | recognition | 3d object recognition | 3d-object-detection-using-scale-invariant-and | convolution |
| computer vision | image, video | recognition | 3d object recognition | 3d-object-detection-using-scale-invariant-and | softmax |
| computer vision | image, video | recognition | 3d object recognition | 3d-object-detection-using-scale-invariant-and | max-pooling |
| computer vision | image, video | recognition | 3d object recognition | 3d-object-detection-using-scale-invariant-and | relu |
| computer vision | image, video | recognition | 3d object recognition | 3d-object-detection-using-scale-invariant-and | he-initialization |
| computer vision | image, video | generation | image generation | image-retrieval | network-dissection |
| computer vision | image, video | generation | image generation | image-retrieval | yolov2 |
| computer vision | image, video | generation | image generation | image-retrieval | average-pooling |
| computer vision | image, video | generation | image generation | image-retrieval | global-average-pooling |
| computer vision | image, video | generation | image generation | image-retrieval | convolution |
| computer vision | image, video | generation | image generation | image-retrieval | softmax |
| computer vision | image, video | generation | image generation | image-retrieval | max-pooling |
| computer vision | image, video | generation | image generation | image-retrieval | darknet-19 |
| computer vision | image, video | generation | image generation | image-retrieval | 1x1-convolution |
| computer vision | image, video | generation | image generation | image-retrieval | batch-normalization |
| computer vision | image, video | classification | image classification | igcv3-interleaved-low-rank-group-convolutions | average-pooling |
| computer vision | image, video | classification | image classification | igcv3-interleaved-low-rank-group-convolutions | pointwise-convolution |
| computer vision | image, video | classification | image classification | igcv3-interleaved-low-rank-group-convolutions | convolution |
| computer vision | image, video | classification | image classification | igcv3-interleaved-low-rank-group-convolutions | depthwise-separable-convolution |
| computer vision | image, video | classification | image classification | igcv3-interleaved-low-rank-group-convolutions | mobilenetv2 |
| computer vision | image, video | classification | image classification | igcv3-interleaved-low-rank-group-convolutions | 1x1-convolution |
| computer vision | image, video | classification | image classification | igcv3-interleaved-low-rank-group-convolutions | depthwise-convolution |
| computer vision | image, video | classification | image classification | igcv3-interleaved-low-rank-group-convolutions | inverted-residual-block |
| computer vision | image, video | classification | image classification | igcv3-interleaved-low-rank-group-convolutions | batch-normalization |
| computer vision | image, video | classification | image classification | adversarial-attacks-on-face-detectors-using | roi-pooling |
| computer vision | image, video | classification | image classification | adversarial-attacks-on-face-detectors-using | convolution |
| computer vision | image, video | classification | image classification | adversarial-attacks-on-face-detectors-using | softmax |
| computer vision | image, video | classification | image classification | adversarial-attacks-on-face-detectors-using | faster-r-cnn |
| computer vision | image, video | classification | image classification | adversarial-attacks-on-face-detectors-using | rpn |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | average-pooling |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | randomhorizontalflip |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | global-average-pooling |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | convolution |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | 1x1-convolution |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | resnext |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | relu |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | resnext-block |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | he-initialization |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | grouped-convolution |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | batch-normalization |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | randomresizedcrop |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | sgd-with-momentum |
| computer vision | image, video | classification | image classification | exploring-the-limits-of-weakly-supervised | residual-connection |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | non-maximum-suppression |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | roi-align |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | convolution |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | softmax |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | weight-decay |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | 1x1-convolution |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | relu |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | step-decay |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | batch-normalization |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | fpn |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | sgd-with-momentum |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | dilated-convolution |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | dilated-bottleneck-with-projection-block |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | average-pooling |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | rpn |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | randomhorizontalflip |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | global-average-pooling |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | dilated-bottleneck-block |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | roi-pooling |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | faster-r-cnn |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | residual-connection |
| computer vision | image, video | classification | image classification | detnet-a-backbone-network-for-object | detnet |
| computer vision | image, video | classification | image classification | dropout-sampling-for-robust-object-detection | dropout |
| computer vision | image, video | classification | image classification | shapeshifter-robust-physical-adversarial | roi-pooling |
| computer vision | image, video | classification | image classification | shapeshifter-robust-physical-adversarial | softmax |
| computer vision | image, video | classification | image classification | shapeshifter-robust-physical-adversarial | convolution |
| computer vision | image, video | classification | image classification | shapeshifter-robust-physical-adversarial | faster-r-cnn |
| computer vision | image, video | classification | image classification | shapeshifter-robust-physical-adversarial | rpn |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | deeplabv3 |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | dilated-convolution |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | relu6 |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | average-pooling |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | rmsprop |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | depthwise-separable-convolution |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | aspp |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | depthwise-convolution |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | residual-connection |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | pointwise-convolution |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | residual-block |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | convolution |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | weight-decay |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | mobilenetv2 |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | 1x1-convolution |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | relu |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | spatial-pyramid-pooling |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | inverted-residual-block |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | dropout |
| computer vision | image, video | classification | image classification | mobilenetv2-inverted-residuals-and-linear | batch-normalization |
| computer vision | image, video | classification | image classification | weakly-supervised-object-localization-on | convolution |
| computer vision | image, video | classification | image classification | weakly-supervised-object-localization-on | fcn |
| computer vision | image, video | classification | image classification | weakly-supervised-object-localization-on | max-pooling |
| computer vision | image, video | classification | image classification | recovering-from-random-pruning-on-the | vgg-16 |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | average-pooling |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | rpn |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | dense-connections |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | alexnet |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | global-average-pooling |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | roi-pooling |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | channel-shuffle |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | faster-r-cnn |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | residual-connection |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | pointwise-convolution |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | softmax |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | local-response-normalization |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | shufflenet-block |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | weight-decay |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | 1x1-convolution |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | dropout |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | randomresizedcrop |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | randomhorizontalflip |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | depthwise-convolution |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | grouped-convolution |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | convolution |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | shufflenet |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | max-pooling |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | relu |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | step-decay |
| computer vision | image, video | classification | image classification | shufflenet-an-extremely-efficient | batch-normalization |
| computer vision | image, video | classification | image classification | sparse-coding-on-stereo-video-for-object | dcnn |
| computer vision | image, video | classification | image classification | random-erasing-data-augmentation | random-erasing |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | global-average-pooling |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | convolution |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | residual-block |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | max-pooling |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | 1x1-convolution |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | relu |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | he-initialization |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | batch-normalization |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | residual-connection |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | bottleneck-residual-block |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | resnet |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | knowledge-distillation |
| computer vision | image, video | classification | image classification | apprentice-using-knowledge-distillation | average-pooling |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | global-average-pooling |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | convolution |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | residual-block |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | max-pooling |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | 1x1-convolution |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | relu |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | he-initialization |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | batch-normalization |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | residual-connection |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | bottleneck-residual-block |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | resnet |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | knowledge-distillation |
| computer vision | image, video | reasoning | knowledge representation and reasoning | apprentice-using-knowledge-distillation | average-pooling |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | sigmoid-activation |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | squeeze-and-excitation-block |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | roi-align |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | convolution |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | residual-block |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | softmax |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | max-pooling |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | 1x1-convolution |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | resnext |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | relu |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | dense-block |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | he-initialization |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | dropout |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | batch-normalization |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | mask-r-cnn |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | resnet |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | average-pooling |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | dense-connections |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | global-average-pooling |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | senet |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | concatenated-skip-connection |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | densenet |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | resnext-block |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | grouped-convolution |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | residual-connection |
| computer vision | image, video | classification | image classification | learning-deep-compositional-grammatical | bottleneck-residual-block |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | convolution |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | residual-block |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | softmax |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | max-pooling |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | weight-decay |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | 1x1-convolution |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | relu |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | he-initialization |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | xavier-initialization |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | step-decay |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | batch-normalization |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | sgd-with-momentum |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | resnet |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | rpn |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | average-pooling |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | global-average-pooling |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | roi-pooling |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | faster-r-cnn |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | rmsprop |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | bottleneck-residual-block |
| computer vision | image, video | classification | image classification | revisiting-unreasonable-effectiveness-of-data | residual-connection |
| computer vision | image, video | classification | image classification | tube-convolutional-neural-network-t-cnn-for | convolution |
| computer vision | image, video | classification | image classification | tube-convolutional-neural-network-t-cnn-for | 3d-convolution |
| computer vision | image, video | classification | image classification | residual-squeeze-vgg16 | convolution |
| computer vision | image, video | classification | image classification | residual-squeeze-vgg16 | 1x1-convolution |
| computer vision | image, video | classification | image classification | residual-squeeze-vgg16 | fire-module |
| computer vision | image, video | classification | image classification | residual-squeeze-vgg16 | relu |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | average-pooling |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | dense-connections |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | randomhorizontalflip |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | global-average-pooling |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | mobilenetv1 |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | depthwise-separable-convolution |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | depthwise-convolution |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | pointwise-convolution |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | softmax |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | convolution |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | exponential-decay |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | 1x1-convolution |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | relu |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | randomresizedcrop |
| computer vision | image, video | classification | image classification | mobilenets-efficient-convolutional-neural | batch-normalization |
| computer vision | image, video | classification | image classification | cross-view-image-matching-for-geo | roi-pooling |
| computer vision | image, video | classification | image classification | cross-view-image-matching-for-geo | convolution |
| computer vision | image, video | classification | image classification | cross-view-image-matching-for-geo | softmax |
| computer vision | image, video | classification | image classification | cross-view-image-matching-for-geo | faster-r-cnn |
| computer vision | image, video | classification | image classification | cross-view-image-matching-for-geo | rpn |
| computer vision | image, video | classification | image classification | improving-training-of-deep-neural-networks | batch-normalization |
| computer vision | image, video | classification | image classification | resfeats-residual-network-based-features-for | pca |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | googlenet |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | average-pooling |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | dense-connections |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | inception-module |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | softmax |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | local-response-normalization |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | convolution |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | max-pooling |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | 1x1-convolution |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | relu |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | dropout |
| computer vision | image, video | classification | image classification | weakly-supervised-learning-of-mid-level | auxiliary-classifier |
| computer vision | image, video | classification | image classification | revisiting-batch-normalization-for-practical | batch-normalization |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | resnet |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | rpn |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | average-pooling |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | global-average-pooling |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | roi-pooling |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | faster-r-cnn |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | bottleneck-residual-block |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | convolution |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | residual-block |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | softmax |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | max-pooling |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | 1x1-convolution |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | relu |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | he-initialization |
| computer vision | image, video | classification | image classification | object-detection-networks-on-convolutional | batch-normalization |
| computer vision | image, video | classification | image classification | object-detection-from-video-tubelets-with | convolution |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | convolution |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | residual-block |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | max-pooling |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | weight-decay |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | 1x1-convolution |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | relu |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | he-initialization |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | batch-normalization |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | step-decay |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | randomresizedcrop |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | sgd-with-momentum |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | resnet |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | average-pooling |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | global-average-pooling |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | randomhorizontalflip |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | residual-connection |
| computer vision | image, video | classification | image classification | deep-residual-learning-for-image-recognition | bottleneck-residual-block |
| computer vision | image, video | classification | image classification | relaxed-multiple-instance-svm-with | svm |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | dense-connections |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | spp-net |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | alexnet |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | randomhorizontalflip |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | zfnet |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | local-contrast-normalization |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | r-cnn |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | svm |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | grouped-convolution |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | sgd |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | convolution |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | overfeat |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | softmax |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | local-response-normalization |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | max-pooling |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | 1x1-convolution |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | spatial-pyramid-pooling |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | relu |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | dropout |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | randomresizedcrop |
| computer vision | image, video | classification | image classification | spatial-pyramid-pooling-in-deep-convolutional | step-decay |
| computer vision | image, video | classification | image classification | boosting-convolutional-features-for-robust | selective-search |
| computer vision | image, video | classification | image classification | compressing-deep-convolutional-networks-using | k-means-clustering |
| computer vision | image, video | classification | image classification | highly-efficient-forward-and-backward | convolution |
| computer vision | image, video | classification | image classification | untangling-local-and-global-deformations-in | convolution |
| computer vision | image, video | classification | image classification | deep-learning-representation-using | autoencoder |
| computer vision | image, video | classification | image classification | hierarchical-adaptive-structural-svm-for | svm |
| computer vision | image, video | classification | image classification | finding-original-image-of-a-sub-image-using | k-nn |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | average-pooling |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | lstm |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | mnasnet |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | dense-connections |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | global-average-pooling |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | randomhorizontalflip |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | depthwise-separable-convolution |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | rmsprop |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | depthwise-convolution |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | tanh-activation |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | sigmoid-activation |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | linear-warmup-with-linear-decay |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | squeeze-and-excitation-block |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | pointwise-convolution |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | convolution |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | softmax |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | weight-decay |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | 1x1-convolution |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | relu |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | inverted-residual-block |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | dropout |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | batch-normalization |
| computer vision | image, video | classification | image classification | mnasnet-platform-aware-neural-architecture | randomresizedcrop |
| computer vision | image, video | classification | image classification | temporal-spatial-mapping-for-action | temporal-attention |
| computer vision | image, video | classification | image classification | revisit-multinomial-logistic-regression-in | softmax |
| computer vision | image, video | classification | image classification | revisit-multinomial-logistic-regression-in | logistic-regression |
| computer vision | image, video | classification | image classification | revisit-multinomial-logistic-regression-in | linear-layer |
| computer vision | image, video | classification | image classification | global-weighted-average-pooling-bridges-pixel | position-sensitive-roi-pooling |
| computer vision | image, video | classification | image classification | global-weighted-average-pooling-bridges-pixel | convolution |
| computer vision | image, video | classification | image classification | global-weighted-average-pooling-bridges-pixel | max-pooling |
| computer vision | image, video | classification | image classification | global-weighted-average-pooling-bridges-pixel | average-pooling |
| computer vision | image, video | classification | image classification | global-weighted-average-pooling-bridges-pixel | r-fcn |
| computer vision | image, video | classification | image classification | dropout-distillation-for-efficiently | dropout |
| computer vision | image, video | classification | image classification | dropout-distillation-for-efficiently | roi-pooling |
| computer vision | image, video | classification | image classification | dropout-distillation-for-efficiently | convolution |
| computer vision | image, video | classification | image classification | dropout-distillation-for-efficiently | softmax |
| computer vision | image, video | classification | image classification | dropout-distillation-for-efficiently | faster-r-cnn |
| computer vision | image, video | classification | image classification | dropout-distillation-for-efficiently | rpn |
| computer vision | image, video | classification | image classification | ktan-knowledge-transfer-adversarial-network | softmax |
| computer vision | image, video | classification | image classification | ktan-knowledge-transfer-adversarial-network | knowledge-distillation |
| computer vision | image, video | reasoning | knowledge representation and reasoning | ktan-knowledge-transfer-adversarial-network | softmax |
| computer vision | image, video | reasoning | knowledge representation and reasoning | ktan-knowledge-transfer-adversarial-network | knowledge-distillation |
| computer vision | image, video | classification | image classification | composite-binary-decomposition-networks | vgg-16 |
| computer vision | image, video | classification | image classification | composite-binary-decomposition-networks | softmax |
| computer vision | image, video | classification | image classification | composite-binary-decomposition-networks | convolution |
| computer vision | image, video | classification | image classification | composite-binary-decomposition-networks | max-pooling |
| computer vision | image, video | classification | image classification | composite-binary-decomposition-networks | segnet |
| computer vision | image, video | classification | image classification | composite-binary-decomposition-networks | relu |
| computer vision | image, video | classification | image classification | composite-binary-decomposition-networks | he-initialization |
| computer vision | image, video | classification | image classification | composite-binary-decomposition-networks | batch-normalization |
| computer vision | image, video | classification | image classification | expandnets-exploiting-linear-redundancy-to | knowledge-distillation |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | espnet |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | dilated-convolution |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | average-pooling |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | dense-connections |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | global-average-pooling |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | residual-connection |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | sigmoid-activation |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | strided-eesp |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | pointwise-convolution |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | espnetv2 |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | softmax |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | 1x1-convolution |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | dropout |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | randomresizedcrop |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | esp |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | lstm |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | hierarchical-feature-fusion |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | randomhorizontalflip |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | concatenated-skip-connection |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | eesp |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | depthwise-separable-convolution |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | cyclical-learning-rate-policy |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | depthwise-convolution |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | grouped-convolution |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | tanh-activation |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | eru |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | sgd |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | prelu |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | convolution |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | depthwise-dilated-separable-convolution |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | groupwise-point-convolution |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | he-initialization |
| computer vision | image, video | classification | image classification | espnetv2-a-light-weight-power-efficient-and | batch-normalization |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | global-average-pooling |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | convolution |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | residual-block |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | max-pooling |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | 1x1-convolution |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | relu |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | he-initialization |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | batch-normalization |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | bottleneck-residual-block |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | residual-connection |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | resnet |
| computer vision | image, video | classification | image classification | imagenet-trained-cnns-are-biased-towards | average-pooling |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | nesterov-accelerated-gradient |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | mixup |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | average-pooling |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | cosine-annealing |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | randomhorizontalflip |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | label-smoothing |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | global-average-pooling |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | bottleneck-residual-block |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | residual-connection |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | resnet-d |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | convolution |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | residual-block |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | max-pooling |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | weight-decay |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | 1x1-convolution |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | relu |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | randomresizedcrop |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | xavier-initialization |
| computer vision | image, video | classification | image classification | bag-of-tricks-for-image-classification-with | batch-normalization |
| computer vision | image, video | classification | image classification | iterative-reorganization-with-weak-spatial | jigsaw |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | googlenet |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | average-pooling |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | dense-connections |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | alexnet |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | inception-module |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | softmax |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | local-response-normalization |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | convolution |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | max-pooling |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | 1x1-convolution |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | relu |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | dropout |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | grouped-convolution |
| computer vision | image, video | classification | image classification | clip-q-deep-network-compression-learning-by | auxiliary-classifier |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | fpn |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | dilated-convolution |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | dilated-bottleneck-with-projection-block |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | average-pooling |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | rpn |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | global-average-pooling |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | dilated-bottleneck-block |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | roi-pooling |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | position-sensitive-roi-pooling |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | faster-r-cnn |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | residual-connection |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | detnet |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | ssd |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | non-maximum-suppression |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | convolution |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | softmax |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | focal-loss |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | 1x1-convolution |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | r-fcn |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | retinanet |
| computer vision | image, video | classification | image classification | detnet-design-backbone-for-object-detection | relu |
| computer vision | image, video | classification | image classification | studying-the-plasticity-in-deep-convolutional | vgg-16 |
| computer vision | image, video | classification | image classification | studying-the-plasticity-in-deep-convolutional | softmax |
| computer vision | image, video | classification | image classification | studying-the-plasticity-in-deep-convolutional | convolution |
| computer vision | image, video | classification | image classification | studying-the-plasticity-in-deep-convolutional | max-pooling |
| computer vision | image, video | classification | image classification | studying-the-plasticity-in-deep-convolutional | segnet |
| computer vision | image, video | classification | image classification | studying-the-plasticity-in-deep-convolutional | relu |
| computer vision | image, video | classification | image classification | studying-the-plasticity-in-deep-convolutional | he-initialization |
| computer vision | image, video | classification | image classification | studying-the-plasticity-in-deep-convolutional | batch-normalization |
| computer vision | image, video | classification | image classification | a-survey-of-the-recent-architectures-of-deep | tanh-activation |
| computer vision | image, video | classification | image classification | a-survey-of-the-recent-architectures-of-deep | mish |
| computer vision | image, video | classification | image classification | a-survey-of-the-recent-architectures-of-deep | softplus |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | googlenet |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | lstm |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | average-pooling |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | dense-connections |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | inception-module |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | auxiliary-classifier |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | tanh-activation |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | sigmoid-activation |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | softmax |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | local-response-normalization |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | convolution |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | max-pooling |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | 1x1-convolution |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | relu |
| computer vision | image, video | classification | image classification | weighted-entropy-based-quantization-for-deep | dropout |
| computer vision | image, video | classification | image classification | robust-visual-tracking-using-oblique-random | svm |
| computer vision | image, video | detection | image detection | image-manipulation-detection | roi-pooling |
| computer vision | image, video | detection | image detection | image-manipulation-detection | convolution |
| computer vision | image, video | detection | image detection | image-manipulation-detection | softmax |
| computer vision | image, video | detection | image detection | image-manipulation-detection | faster-r-cnn |
| computer vision | image, video | detection | image detection | image-manipulation-detection | rpn |
| computer vision | image, video | generation | image generation | image-manipulation | roi-pooling |
| computer vision | image, video | generation | image generation | image-manipulation | convolution |
| computer vision | image, video | generation | image generation | image-manipulation | softmax |
| computer vision | image, video | generation | image generation | image-manipulation | faster-r-cnn |
| computer vision | image, video | generation | image generation | image-manipulation | rpn |
| computer vision | image, video | generation | image detection | human detection | convolution |
| computer vision | image, video | generation | image detection | human detection | svm |
| computer vision | image, video | recognition | image recognition | scene-understanding | roi-pooling |
| computer vision | image, video | recognition | image recognition | scene-understanding | convolution |
| computer vision | image, video | recognition | image recognition | scene-understanding | softmax |
| computer vision | image, video | recognition | image recognition | scene-understanding | faster-r-cnn |
| computer vision | image, video | recognition | image recognition | scene-understanding | rpn |
| computer vision | image, video | recognition | image recognition | scene-understanding | convolution |
| computer vision | image, video | recognition | image recognition | scene-understanding | fcn |
| computer vision | image, video | recognition | image recognition | scene-understanding | max-pooling |
| computer vision | image, video | recognition | image recognition | scene-understanding | 1x1-convolution |
| computer vision | image, video | recognition | image recognition | scene-understanding | relu |
| computer vision | image, video | recognition | image recognition | scene-understanding | he-initialization |
| computer vision | image, video | recognition | image recognition | scene-understanding | batch-normalization |
| computer vision | image, video | recognition | image recognition | scene-understanding | resnet |
| computer vision | image, video | recognition | image recognition | scene-understanding | deeplab |
| computer vision | image, video | recognition | image recognition | scene-understanding | dilated-convolution |
| computer vision | image, video | recognition | image recognition | scene-understanding | crf |
| computer vision | image, video | recognition | image recognition | scene-understanding | average-pooling |
| computer vision | image, video | recognition | image recognition | scene-understanding | dense-connections |
| computer vision | image, video | recognition | image recognition | scene-understanding | global-average-pooling |
| computer vision | image, video | recognition | image recognition | scene-understanding | residual-connection |
| computer vision | image, video | recognition | image recognition | scene-understanding | bottleneck-residual-block |
| computer vision | image, video | recognition | image recognition | scene-understanding | feedforward-network |
| computer vision | image, video | recognition | image recognition | scene-understanding | convolution |
| computer vision | image, video | recognition | image recognition | scene-understanding | residual-block |
| computer vision | image, video | recognition | image recognition | scene-understanding | max-pooling |
| computer vision | image, video | recognition | image recognition | scene-understanding | vgg-16 |
| computer vision | image, video | recognition | image recognition | depth-estimation | roi-pooling |
| computer vision | image, video | recognition | image recognition | depth-estimation | convolution |
| computer vision | image, video | recognition | image recognition | depth-estimation | softmax |
| computer vision | image, video | recognition | image recognition | depth-estimation | faster-r-cnn |
| computer vision | image, video | recognition | image recognition | depth-estimation | rpn |
| computer vision | image, video | recognition | image recognition | depth-estimation | carla |
| computer vision | image, video | recognition | image recognition | depth-estimation | convolution |
| computer vision | image, video | recognition | image recognition | depth-estimation | fcn |
| computer vision | image, video | recognition | image recognition | depth-estimation | max-pooling |
| computer vision | image, video | recognition | image recognition | depth-estimation | global-average-pooling |
| computer vision | image, video | recognition | image recognition | depth-estimation | non-maximum-suppression |
| computer vision | image, video | recognition | image recognition | depth-estimation | convolution |
| computer vision | image, video | recognition | image recognition | depth-estimation | residual-block |
| computer vision | image, video | recognition | image recognition | depth-estimation | max-pooling |
| computer vision | image, video | recognition | image recognition | depth-estimation | 1x1-convolution |
| computer vision | image, video | recognition | image recognition | depth-estimation | relu |
| computer vision | image, video | recognition | image recognition | depth-estimation | he-initialization |
| computer vision | image, video | recognition | image recognition | depth-estimation | batch-normalization |
| computer vision | image, video | recognition | image recognition | depth-estimation | bottleneck-residual-block |
| computer vision | image, video | recognition | image recognition | depth-estimation | residual-connection |
| computer vision | image, video | recognition | image recognition | depth-estimation | resnet |
| computer vision | image, video | recognition | image recognition | depth-estimation | ssd |
| computer vision | image, video | recognition | image recognition | depth-estimation | average-pooling |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | global-average-pooling |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | non-maximum-suppression |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | softmax |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | convolution |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | max-pooling |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | 1x1-convolution |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | fire-module |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | relu |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | dropout |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | xavier-initialization |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | residual-connection |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | squeezenet |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | ssd |
| computer vision | image, video | detection | object detection | tiny-ssd-a-tiny-single-shot-detection-deep | average-pooling |
| computer vision | image, video | detection | object detection | mask-r-cnn | roi-align |
| computer vision | image, video | detection | object detection | mask-r-cnn | convolution |
| computer vision | image, video | detection | object detection | mask-r-cnn | softmax |
| computer vision | image, video | detection | object detection | mask-r-cnn | residual-block |
| computer vision | image, video | detection | object detection | mask-r-cnn | max-pooling |
| computer vision | image, video | detection | object detection | mask-r-cnn | 1x1-convolution |
| computer vision | image, video | detection | object detection | mask-r-cnn | resnext |
| computer vision | image, video | detection | object detection | mask-r-cnn | relu |
| computer vision | image, video | detection | object detection | mask-r-cnn | he-initialization |
| computer vision | image, video | detection | object detection | mask-r-cnn | batch-normalization |
| computer vision | image, video | detection | object detection | mask-r-cnn | mask-r-cnn |
| computer vision | image, video | detection | object detection | mask-r-cnn | resnet |
| computer vision | image, video | detection | object detection | mask-r-cnn | average-pooling |
| computer vision | image, video | detection | object detection | mask-r-cnn | global-average-pooling |
| computer vision | image, video | detection | object detection | mask-r-cnn | resnext-block |
| computer vision | image, video | detection | object detection | mask-r-cnn | grouped-convolution |
| computer vision | image, video | detection | object detection | mask-r-cnn | residual-connection |
| computer vision | image, video | detection | object detection | mask-r-cnn | bottleneck-residual-block |
| computer vision | image, video | detection | object detection | fast-yolo-a-fast-you-only-look-once-system | yolov2 |
| computer vision | image, video | detection | object detection | fast-yolo-a-fast-you-only-look-once-system | average-pooling |
| computer vision | image, video | detection | object detection | fast-yolo-a-fast-you-only-look-once-system | global-average-pooling |
| computer vision | image, video | detection | object detection | fast-yolo-a-fast-you-only-look-once-system | convolution |
| computer vision | image, video | detection | object detection | fast-yolo-a-fast-you-only-look-once-system | softmax |
| computer vision | image, video | detection | object detection | fast-yolo-a-fast-you-only-look-once-system | max-pooling |
| computer vision | image, video | detection | object detection | fast-yolo-a-fast-you-only-look-once-system | darknet-19 |
| computer vision | image, video | detection | object detection | fast-yolo-a-fast-you-only-look-once-system | 1x1-convolution |
| computer vision | image, video | detection | object detection | fast-yolo-a-fast-you-only-look-once-system | batch-normalization |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | global-average-pooling |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | residual-block |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | convolution |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | max-pooling |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | 1x1-convolution |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | relu |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | he-initialization |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | batch-normalization |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | residual-connection |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | bottleneck-residual-block |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | resnet |
| computer vision | image, video | detection | object detection | wide-residual-inception-networks-for-real | average-pooling |
| computer vision | image, video | detection | object detection | yes-net-an-effective-detector-based-on-global | yolov2 |
| computer vision | image, video | detection | object detection | yes-net-an-effective-detector-based-on-global | ssd |
| computer vision | image, video | detection | object detection | yes-net-an-effective-detector-based-on-global | average-pooling |
| computer vision | image, video | detection | object detection | yes-net-an-effective-detector-based-on-global | non-maximum-suppression |
| computer vision | image, video | detection | object detection | yes-net-an-effective-detector-based-on-global | global-average-pooling |
| computer vision | image, video | detection | object detection | yes-net-an-effective-detector-based-on-global | convolution |
| computer vision | image, video | detection | object detection | yes-net-an-effective-detector-based-on-global | softmax |
| computer vision | image, video | detection | object detection | yes-net-an-effective-detector-based-on-global | max-pooling |
| computer vision | image, video | detection | object detection | yes-net-an-effective-detector-based-on-global | darknet-19 |
| computer vision | image, video | detection | object detection | yes-net-an-effective-detector-based-on-global | 1x1-convolution |
| computer vision | image, video | detection | object detection | yes-net-an-effective-detector-based-on-global | batch-normalization |
| computer vision | image, video | detection | object detection | relief-r-cnn-utilizing-convolutional-features | r-cnn |
| computer vision | image, video | detection | object detection | relief-r-cnn-utilizing-convolutional-features | convolution |
| computer vision | image, video | detection | object detection | relief-r-cnn-utilizing-convolutional-features | max-pooling |
| computer vision | image, video | detection | object detection | relief-r-cnn-utilizing-convolutional-features | svm |
| computer vision | image, video | detection | object detection | vote3deep-fast-object-detection-in-3d-point | sparse-convolutions |
| computer vision | image, video | detection | object detection | vote3deep-fast-object-detection-in-3d-point | feature-centric-voting |
| computer vision | image, video | detection | object detection | vote3deep-fast-object-detection-in-3d-point | relu |
| computer vision | image, video | detection | object detection | vote3deep-fast-object-detection-in-3d-point | non-maximum-suppression |
| computer vision | image, video | detection | object detection | vote3deep-fast-object-detection-in-3d-point | l1-regularization |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | non-maximum-suppression |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | softmax |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | weight-decay |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | darknet-19 |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | randomresizedcrop |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | colorjitter |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | step-decay |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | sgd-with-momentum |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | polynomial-rate-decay |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | yolov2 |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | fast-yolov2 |
| computer vision | image, video | detection | object detection | yolo9000-better-faster-stronger | ssd |
| computer vision | image, video | detection | object detection | pvanet-deep-but-lightweight-neural-networks | relu |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | average-pooling |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | global-average-pooling |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | convolution |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | residual-block |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | max-pooling |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | 1x1-convolution |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | r-fcn |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | relu |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | he-initialization |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | batch-normalization |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | residual-connection |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | bottleneck-residual-block |
| computer vision | image, video | detection | object detection | r-fcn-object-detection-via-region-based-fully | resnet |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | non-maximum-suppression |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | softmax |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | convolution |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | max-pooling |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | 1x1-convolution |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | relu |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | dropout |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | step-decay |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | randomresizedcrop |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | sgd-with-momentum |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | leaky-relu |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | dense-connections |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | yolov1 |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | roi-pooling |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | vgg |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | fast-r-cnn |
| computer vision | image, video | detection | object detection | you-only-look-once-unified-real-time-object | colorjitter |
| computer vision | image, video | detection | object detection | faster-r-cnn-towards-real-time-object | rpn |
| computer vision | image, video | detection | object detection | faster-r-cnn-towards-real-time-object | fast-r-cnn |
| computer vision | image, video | detection | object detection | faster-r-cnn-towards-real-time-object | roi-pooling |
| computer vision | image, video | detection | object detection | faster-r-cnn-towards-real-time-object | vgg-16 |
| computer vision | image, video | detection | object detection | faster-r-cnn-towards-real-time-object | convolution |
| computer vision | image, video | detection | object detection | faster-r-cnn-towards-real-time-object | softmax |
| computer vision | image, video | detection | object detection | faster-r-cnn-towards-real-time-object | faster-r-cnn |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | average-pooling |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | lstm |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | mnasnet |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | dense-connections |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | global-average-pooling |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | randomhorizontalflip |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | depthwise-separable-convolution |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | rmsprop |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | depthwise-convolution |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | tanh-activation |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | sigmoid-activation |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | linear-warmup-with-linear-decay |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | squeeze-and-excitation-block |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | pointwise-convolution |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | convolution |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | softmax |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | weight-decay |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | 1x1-convolution |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | relu |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | inverted-residual-block |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | dropout |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | batch-normalization |
| computer vision | image, video | detection | object detection | mnasnet-platform-aware-neural-architecture | randomresizedcrop |
| computer vision | image, video | detection | object detection | yolo-lite-a-real-time-object-detection | convolution |
| computer vision | image, video | detection | object detection | yolo-lite-a-real-time-object-detection | ssd |
| computer vision | image, video | detection | object detection | yolo-lite-a-real-time-object-detection | 1x1-convolution |
| computer vision | image, video | detection | object detection | yolo-lite-a-real-time-object-detection | non-maximum-suppression |
| computer vision | image, video | detection | object detection | fast-object-detection-in-compressed-video | convolution |
| computer vision | image, video | detection | object detection | fast-object-detection-in-compressed-video | position-sensitive-roi-pooling |
| computer vision | image, video | detection | object detection | fast-object-detection-in-compressed-video | memory-network |
| computer vision | image, video | detection | object detection | fast-object-detection-in-compressed-video | r-fcn |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | espnet |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | dilated-convolution |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | average-pooling |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | dense-connections |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | global-average-pooling |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | residual-connection |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | sigmoid-activation |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | strided-eesp |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | pointwise-convolution |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | espnetv2 |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | softmax |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | 1x1-convolution |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | dropout |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | randomresizedcrop |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | esp |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | lstm |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | hierarchical-feature-fusion |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | randomhorizontalflip |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | concatenated-skip-connection |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | eesp |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | depthwise-separable-convolution |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | cyclical-learning-rate-policy |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | depthwise-convolution |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | grouped-convolution |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | tanh-activation |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | eru |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | sgd |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | prelu |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | convolution |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | depthwise-dilated-separable-convolution |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | groupwise-point-convolution |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | he-initialization |
| computer vision | image, video | detection | object detection | espnetv2-a-light-weight-power-efficient-and | batch-normalization |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | non-maximum-suppression |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | convolution |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | softmax |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | max-pooling |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | weight-decay |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | 1x1-convolution |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | relu |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | batch-normalization |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | step-decay |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | sgd-with-momentum |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | average-pooling |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | two-way-dense-layer |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | dense-connections |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | cosine-annealing |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | global-average-pooling |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | peleenet |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | bottleneck-residual-block |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | residual-connection |
| computer vision | image, video | detection | object detection | pelee-a-real-time-object-detection-system-on-1 | ssd |
| computer vision | image, video | detection | object detection | 3d-regression-neural-network-for-the | convolution |
| computer vision | image, video | detection | object detection | feature-fused-ssd-fast-detection-for-small | convolution |
| computer vision | image, video | detection | object detection | feature-fused-ssd-fast-detection-for-small | ssd |
| computer vision | image, video | detection | object detection | feature-fused-ssd-fast-detection-for-small | 1x1-convolution |
| computer vision | image, video | detection | object detection | feature-fused-ssd-fast-detection-for-small | non-maximum-suppression |
| computer vision | image, video | detection | object detection | perceptual-generative-adversarial-networks | gan |
| computer vision | image, video | detection | object detection | perceptual-generative-adversarial-networks | convolution |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | resnet |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | average-pooling |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | dense-connections |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | alexnet |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | global-average-pooling |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | grouped-convolution |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | residual-connection |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | bottleneck-residual-block |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | softmax |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | local-response-normalization |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | residual-block |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | convolution |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | max-pooling |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | 1x1-convolution |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | relu |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | dropout |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | he-initialization |
| computer vision | image, video | reasoning | video recognition | recurrent-residual-module-for-fast-inference | batch-normalization |
| computer vision | image, video | detection | medical detection | breast-cancer-detection | roi-pooling |
| computer vision | image, video | detection | medical detection | breast-cancer-detection | softmax |
| computer vision | image, video | detection | medical detection | breast-cancer-detection | convolution |
| computer vision | image, video | detection | medical detection | breast-cancer-detection | faster-r-cnn |
| computer vision | image, video | detection | medical detection | breast-cancer-detection | rpn |
| computer vision | image, video | segmentation | medical segmentation | lesion-segmentation | ran |
| computer vision | image, video | detection | medical detection | organ-detection | rpn |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | roi-align |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | convolution |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | softmax |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | residual-block |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | max-pooling |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | resnext |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | relu |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | he-initialization |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | batch-normalization |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | mask-r-cnn |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | resnet |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | average-pooling |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | resnext-block |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | residual-connection |
| computer vision | image, video | segmentation | medical segmentation | nuclear-segmentation | bottleneck-residual-block |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | roi-align |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | convolution |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | softmax |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | residual-block |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | max-pooling |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | resnext |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | relu |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | he-initialization |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | batch-normalization |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | mask-r-cnn |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | resnet |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | average-pooling |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | resnext-block |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | residual-connection |
| computer vision | image, video | segmentation | medical segmentation | multi-tissue-nucleus-segmentation | bottleneck-residual-block |
| computer vision | image, video | detection | medical detection | breast-cancer-detection | roi-pooling |
| computer vision | image, video | detection | medical detection | breast-cancer-detection | softmax |
| computer vision | image, video | detection | medical detection | breast-cancer-detection | convolution |
| computer vision | image, video | detection | medical detection | breast-cancer-detection | faster-r-cnn |
| computer vision | image, video | detection | medical detection | breast-cancer-detection | rpn |
| computer vision | image, video | classification | action classification | non-local-neural-networks | roi-pooling |
| computer vision | image, video | classification | action classification | non-local-neural-networks | convolution |
| computer vision | image, video | classification | action classification | non-local-neural-networks | softmax |
| computer vision | image, video | classification | action classification | non-local-neural-networks | faster-r-cnn |
| computer vision | image, video | classification | action classification | non-local-neural-networks | rpn |
| computer vision | image, video | classification | action classification | non-local-neural-networks | convolution |
| computer vision | image, video | classification | action classification | a-proposal-based-solution-to-spatio-temporal | residual-block |
| computer vision | image, video | classification | action classification | rethinking-the-faster-r-cnn-architecture-for | max-pooling |
| computer vision | image, video | classification | action classification | rethinking-the-faster-r-cnn-architecture-for | non-local-operation |
| computer vision | image, video | classification | action classification | rethinking-the-faster-r-cnn-architecture-for | embedded-dot-product-affinity |
| computer vision | image, video | classification | action classification | rethinking-the-faster-r-cnn-architecture-for | weight-decay |
| computer vision | image, video | classification | action classification | rethinking-the-faster-r-cnn-architecture-for | 1x1-convolution |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | resnext |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | relu |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | he-initialization |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | concatenation-affinity |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | batch-normalization |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | sgd-with-momentum |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | resnet |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | embedded-gaussian-affinity |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | average-pooling |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | global-average-pooling |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | resnext-block |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | grouped-convolution |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | residual-connection |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | bottleneck-residual-block |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | non-local-block |
| computer vision | image, video | classification | action classification | detnet-a-backbone-network-for-object | temporal-jittering |
| computer vision | image, video | detection | action detection | detnet-a-backbone-network-for-object | convolution |
| computer vision | image, video | detection | action detection | detnet-a-backbone-network-for-object | 3d-convolution |
| computer vision | image, video | detection | action detection | detnet-a-backbone-network-for-object | temporal-jittering |
| computer vision | image, video | detection | action detection | detnet-a-backbone-network-for-object | tanh-activation |
| computer vision | image, video | detection | action detection | detnet-a-backbone-network-for-object | lstm |
| computer vision | image, video | detection | action detection | detnet-a-backbone-network-for-object | sigmoid-activation |
| computer vision | image, video | recognition | image recognition | action recognition | roi-pooling |
| computer vision | image, video | recognition | image recognition | action recognition | convolution |
| computer vision | image, video | recognition | image recognition | action recognition | softmax |
| computer vision | image, video | recognition | image recognition | action recognition | faster-r-cnn |
| computer vision | image, video | recognition | image recognition | action recognition | rpn |
| computer vision | image, video | recognition | image recognition | action recognition | temporal-attention |
| computer vision | image, video | recognition | image recognition | action recognition | tanh-activation |
| computer vision | image, video | recognition | image recognition | action recognition | lstm |
| computer vision | image, video | recognition | image recognition | action recognition | sigmoid-activation |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | convolution |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | residual-block |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | max-pooling |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | non-local-operation |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | embedded-dot-product-affinity |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | weight-decay |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | 1x1-convolution |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | resnext |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | relu |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | he-initialization |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | concatenation-affinity |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | batch-normalization |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | sgd-with-momentum |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | resnet |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | embedded-gaussian-affinity |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | average-pooling |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | global-average-pooling |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | resnext-block |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | grouped-convolution |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | residual-connection |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | bottleneck-residual-block |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | non-local-block |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | temporal-attention |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | tanh-activation |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | lstm |
| computer vision | image, video | recognition | video recognition | action-recognition-in-videos | sigmoid-activation |
| computer vision | image, video | classification | image classification | weakly supervised classification | gan |
| computer vision | image, video | classification | image classification | weakly supervised classification | convolution |
| computer vision | image, video | classification | image classification | weakly supervised classification | softmax |
| computer vision | image, video | classification | image classification | weakly supervised classification | convolution |
| computer vision | image, video | classification | image classification | weakly supervised classification | fcn |
| computer vision | image, video | classification | image classification | weakly supervised classification | max-pooling |
| computer vision | image, video | classification | image classification | weakly supervised classification | tanh-activation |
| computer vision | image, video | classification | image classification | weakly supervised classification | memory-network |
| computer vision | image, video | classification | image classification | weakly supervised classification | lstm |
| computer vision | image, video | classification | image classification | weakly supervised classification | sigmoid-activation |
| computer vision | image, video | classification | image classification | weakly supervised classification | googlenet |
| computer vision | image, video | classification | image classification | weakly supervised classification | average-pooling |
| computer vision | image, video | classification | image classification | weakly supervised classification | dense-connections |
| computer vision | image, video | classification | image classification | weakly supervised classification | inception-module |
| computer vision | image, video | classification | image classification | weakly supervised classification | softmax |
| computer vision | image, video | classification | image classification | weakly supervised classification | local-response-normalization |
| computer vision | image, video | classification | image classification | weakly supervised classification | convolution |
| computer vision | image, video | classification | image classification | weakly supervised classification | max-pooling |
| computer vision | image, video | classification | image classification | weakly supervised classification | 1x1-convolution |
| computer vision | image, video | classification | image classification | weakly supervised classification | relu |
| computer vision | image, video | classification | image classification | weakly supervised classification | dropout |
| computer vision | image, video | classification | image classification | weakly supervised classification | auxiliary-classifier |
| computer vision | image, video | classification | image classification | weakly supervised classification | convolution |
| computer vision | image, video | classification | image classification | weakly supervised classification | ssd |
| computer vision | image, video | classification | image classification | weakly supervised classification | 1x1-convolution |
| computer vision | image, video | classification | image classification | weakly supervised classification | non-maximum-suppression |
| computer vision | image, video | classification | image classification | weakly supervised classification | convolution |
| computer vision | image, video | classification | image classification | weakly supervised classification | fcn |
| computer vision | image, video | classification | image classification | weakly supervised classification | max-pooling |
| computer vision | image, video | detection | video detection | fish-detection | nan |
| computer vision | image, video | detection | image detection | window-detection | convolution |
| computer vision | image, video | detection | video detection | video-object-detection | gru |
| computer vision | image, video | detection | video detection | video-object-detection | resnet |
| computer vision | image, video | detection | video detection | video-object-detection | average-pooling |
| computer vision | image, video | detection | video detection | video-object-detection | dense-connections |
| computer vision | image, video | detection | video detection | video-object-detection | alexnet |
| computer vision | image, video | detection | video detection | video-object-detection | global-average-pooling |
| computer vision | image, video | detection | video detection | video-object-detection | grouped-convolution |
| computer vision | image, video | detection | video detection | video-object-detection | residual-connection |
| computer vision | image, video | detection | video detection | video-object-detection | bottleneck-residual-block |
| computer vision | image, video | detection | video detection | video-object-detection | softmax |
| computer vision | image, video | detection | video detection | video-object-detection | local-response-normalization |
| computer vision | image, video | detection | video detection | video-object-detection | residual-block |
| computer vision | image, video | detection | video detection | video-object-detection | convolution |
| computer vision | image, video | detection | video detection | video-object-detection | max-pooling |
| computer vision | image, video | detection | video detection | video-object-detection | 1x1-convolution |
| computer vision | image, video | detection | video detection | video-object-detection | relu |
| computer vision | image, video | detection | video detection | video-object-detection | dropout |
| computer vision | image, video | detection | video detection | video-object-detection | he-initialization |
| computer vision | image, video | detection | video detection | video-object-detection | batch-normalization |
| computer vision | image, video | detection | video detection | video-object-detection | tanh-activation |
| computer vision | image, video | detection | video detection | video-object-detection | memory-network |
| computer vision | image, video | detection | video detection | video-object-detection | lstm |
| computer vision | image, video | detection | video detection | video-object-detection | sigmoid-activation |
| computer vision | image, video | detection | video detection | video-object-detection | convolution |
| computer vision | image, video | detection | video detection | video-object-detection | ssd |
| computer vision | image, video | detection | video detection | video-object-detection | 1x1-convolution |
| computer vision | image, video | detection | video detection | video-object-detection | non-maximum-suppression |
| computer vision | image, video | segmentation | video segmentation | video-object-segmentation | tanh-activation |
| computer vision | image, video | segmentation | video segmentation | video-object-segmentation | convolution |
| computer vision | image, video | segmentation | video segmentation | video-object-segmentation | dilated-convolution |
| computer vision | image, video | segmentation | video segmentation | video-object-segmentation | sigmoid-activation |
| computer vision | image, video | segmentation | video segmentation | video-object-segmentation | convlstm |
| computer vision | image, video | segmentation | video detection | video-salient-object-detection | tanh-activation |
| computer vision | image, video | segmentation | video detection | video-salient-object-detection | convolution |
| computer vision | image, video | segmentation | video detection | video-salient-object-detection | fcn |
| computer vision | image, video | segmentation | video detection | video-salient-object-detection | max-pooling |
| computer vision | image, video | segmentation | video detection | video-salient-object-detection | lstm |
| computer vision | image, video | segmentation | video detection | video-salient-object-detection | sigmoid-activation |
| computer vision | image, video | segmentation | video detection | video-salient-object-detection | tanh-activation |
| computer vision | image, video | segmentation | video detection | video-salient-object-detection | convolution |
| computer vision | image, video | segmentation | video detection | video-salient-object-detection | dilated-convolution |
| computer vision | image, video | segmentation | video detection | video-salient-object-detection | sigmoid-activation |
| computer vision | image, video | segmentation | video detection | video-salient-object-detection | convlstm |
| computer vision | image, video | segmentation | video segmentation | video-semantic-segmentation | ccnet |
| computer vision | image, video | segmentation | video segmentation | video-semantic-segmentation | non-local-block |
| computer vision | image, video | segmentation | video segmentation | video-semantic-segmentation | residual-connection |
| computer vision | image, video | segmentation | video segmentation | video-semantic-segmentation | non-local-operation |
| computer vision | image, video | segmentation | video segmentation | video-semantic-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | video segmentation | video-semantic-segmentation | tanh-activation |
| computer vision | image, video | segmentation | video segmentation | video-semantic-segmentation | convolution |
| computer vision | image, video | segmentation | video segmentation | video-semantic-segmentation | dilated-convolution |
| computer vision | image, video | segmentation | video segmentation | video-semantic-segmentation | sigmoid-activation |
| computer vision | image, video | segmentation | video segmentation | video-semantic-segmentation | convlstm |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | global-average-pooling |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | convolution |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | residual-block |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | max-pooling |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | npid |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | 1x1-convolution |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | relu |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | he-initialization |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | batch-normalization |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | bottleneck-residual-block |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | residual-connection |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | resnet |
| computer vision | image, video | classification | image classification | semi-supervised-image-classification | average-pooling |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | global-average-pooling |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | convolution |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | residual-block |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | max-pooling |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | npid |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | 1x1-convolution |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | relu |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | he-initialization |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | batch-normalization |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | bottleneck-residual-block |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | residual-connection |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | resnet |
| computer vision | image, video | classification | image classification | self-supervised-image-classification | average-pooling |
| computer vision | image, video | detection | text detection | scene-text-detection | rpn |
| computer vision | image, video | detection | text detection | scene-text-detection | r-fcn |
| computer vision | image, video | detection | text detection | scene-text-detection | roi-pooling |
| computer vision | image, video | detection | text detection | scene-text-detection | convolution |
| computer vision | image, video | detection | text detection | scene-text-detection | softmax |
| computer vision | image, video | detection | text detection | scene-text-detection | position-sensitive-roi-pooling |
| computer vision | image, video | detection | text detection | scene-text-detection | faster-r-cnn |
| computer vision | image, video | detection | text detection | scene-text-detection | rpn |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | sgd-with-momentum |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | deeplab |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | feedforward-network |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | crf |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | dense-connections |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | vgg |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | weight-decay |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | scene-segmentation | dropout |
| computer vision | image, video | segmentation | image classification | scene-classification | pca |
| computer vision | image, video | segmentation | image classification | scene-classification | 1x1-convolution |
| computer vision | image, video | segmentation | image classification | scene-classification | relu |
| computer vision | image, video | segmentation | image classification | scene-classification | he-initialization |
| computer vision | image, video | segmentation | image classification | scene-classification | batch-normalization |
| computer vision | image, video | segmentation | image classification | scene-classification | resnet |
| computer vision | image, video | segmentation | image classification | scene-classification | deeplab |
| computer vision | image, video | segmentation | image classification | scene-classification | dilated-convolution |
| computer vision | image, video | segmentation | image classification | scene-classification | crf |
| computer vision | image, video | segmentation | image classification | scene-classification | average-pooling |
| computer vision | image, video | segmentation | image classification | scene-classification | dense-connections |
| computer vision | image, video | segmentation | image classification | scene-classification | global-average-pooling |
| computer vision | image, video | segmentation | image classification | scene-classification | residual-connection |
| computer vision | image, video | segmentation | image classification | scene-classification | bottleneck-residual-block |
| computer vision | image, video | segmentation | image classification | scene-classification | feedforward-network |
| computer vision | image, video | segmentation | image classification | scene-classification | convolution |
| computer vision | image, video | segmentation | image classification | scene-classification | residual-block |
| computer vision | image, video | segmentation | image classification | scene-classification | max-pooling |
| computer vision | image, video | segmentation | image classification | scene-classification | global-average-pooling |
| computer vision | image, video | segmentation | image classification | scene-classification | non-maximum-suppression |
| computer vision | image, video | segmentation | image classification | scene-classification | convolution |
| computer vision | image, video | segmentation | image classification | scene-classification | residual-block |
| computer vision | image, video | segmentation | image classification | scene-classification | max-pooling |
| computer vision | image, video | segmentation | image classification | scene-classification | 1x1-convolution |
| computer vision | image, video | segmentation | image classification | scene-classification | relu |
| computer vision | image, video | segmentation | image classification | scene-classification | he-initialization |
| computer vision | image, video | segmentation | image classification | scene-classification | batch-normalization |
| computer vision | image, video | segmentation | image classification | scene-classification | bottleneck-residual-block |
| computer vision | image, video | segmentation | image classification | scene-classification | residual-connection |
| computer vision | image, video | segmentation | image classification | scene-classification | resnet |
| computer vision | image, video | segmentation | image classification | scene-classification | ssd |
| computer vision | image, video | segmentation | image classification | scene-classification | average-pooling |
| computer vision | image, video | detection | object detection | salient-object-detection | hierarchical-feature-fusion |
| computer vision | image, video | detection | object detection | salient-object-detection | crf |
| computer vision | image, video | detection | object detection | salient-object-detection | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection | fcn |
| computer vision | image, video | detection | object detection | salient-object-detection | max-pooling |
| computer vision | image, video | detection | object detection | salient-object-detection | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection | fast-r-cnn |
| computer vision | image, video | detection | object detection | salient-object-detection | roi-pooling |
| computer vision | image, video | detection | object detection | salient-object-detection | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection | softmax |
| computer vision | image, video | detection | object detection | salient-object-detection | dropout |
| computer vision | image, video | detection | object detection | salient-object-detection | svm |
| computer vision | image, video | detection | object detection | salient-object-detection | crf |
| computer vision | image, video | detection | object detection | salient-object-detection | svm |
| computer vision | image, video | detection | object detection | salient-object-detection | svm |
| computer vision | image, video | detection | object detection | salient-object-detection | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection | fcn |
| computer vision | image, video | detection | object detection | salient-object-detection | max-pooling |
| computer vision | image, video | detection | object detection | salient-object-detection | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection | max-pooling |
| computer vision | image, video | detection | object detection | salient-object-detection | relu |
| computer vision | image, video | detection | object detection | salient-object-detection | u-net |
| computer vision | image, video | detection | object detection | salient-object-detection | concatenated-skip-connection |
| computer vision | image, video | detection | object detection | salient-object-detection | tanh-activation |
| computer vision | image, video | detection | object detection | salient-object-detection | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection | fcn |
| computer vision | image, video | detection | object detection | salient-object-detection | max-pooling |
| computer vision | image, video | detection | object detection | salient-object-detection | lstm |
| computer vision | image, video | detection | object detection | salient-object-detection | sigmoid-activation |
| computer vision | image, video | detection | object detection | salient-object-detection | tanh-activation |
| computer vision | image, video | detection | object detection | salient-object-detection | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection | dilated-convolution |
| computer vision | image, video | detection | object detection | salient-object-detection | sigmoid-activation |
| computer vision | image, video | detection | object detection | salient-object-detection | convlstm |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | hierarchical-feature-fusion |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | crf |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | fcn |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | max-pooling |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | fast-r-cnn |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | roi-pooling |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | softmax |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | dropout |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | svm |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | crf |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | svm |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | svm |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | fcn |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | max-pooling |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | max-pooling |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | relu |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | u-net |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | concatenated-skip-connection |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | tanh-activation |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | fcn |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | max-pooling |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | lstm |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | sigmoid-activation |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | tanh-activation |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | convolution |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | dilated-convolution |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | sigmoid-activation |
| computer vision | image, video | detection | object detection | salient-object-detection-1 | convlstm |
| computer vision | image, video | detection | object detection | saliency-detection | convolution |
| computer vision | image, video | detection | object detection | saliency-detection | fcn |
| computer vision | image, video | detection | object detection | saliency-detection | max-pooling |
| computer vision | image, video | detection | object detection | saliency-detection | fast-r-cnn |
| computer vision | image, video | detection | object detection | saliency-detection | roi-pooling |
| computer vision | image, video | detection | object detection | saliency-detection | convolution |
| computer vision | image, video | detection | object detection | saliency-detection | softmax |
| computer vision | image, video | detection | object detection | saliency-detection | dropout |
| computer vision | image, video | detection | object detection | saliency-detection | convolution |
| computer vision | image, video | detection | object detection | saliency-detection | max-pooling |
| computer vision | image, video | detection | object detection | saliency-detection | relu |
| computer vision | image, video | detection | object detection | saliency-detection | u-net |
| computer vision | image, video | detection | object detection | saliency-detection | concatenated-skip-connection |
| computer vision | image, video | detection | object detection | saliency-detection | tanh-activation |
| computer vision | image, video | detection | object detection | saliency-detection | convolution |
| computer vision | image, video | detection | object detection | saliency-detection | fcn |
| computer vision | image, video | detection | object detection | saliency-detection | max-pooling |
| computer vision | image, video | detection | object detection | saliency-detection | lstm |
| computer vision | image, video | detection | object detection | saliency-detection | sigmoid-activation |
| computer vision | image, video | detection | object detection | saliency-prediction | convolution |
| computer vision | image, video | detection | object detection | saliency-prediction | max-pooling |
| computer vision | image, video | detection | object detection | saliency-prediction | relu |
| computer vision | image, video | detection | object detection | saliency-prediction | u-net |
| computer vision | image, video | detection | object detection | saliency-prediction | concatenated-skip-connection |
| computer vision | image, video | classification | image classification | superpixel-image-classification | monet |
| computer vision | image, video | detection | object detection | robust-object-detection | dropout |
| computer vision | image, video | detection | object detection | robust-object-detection | roi-pooling |
| computer vision | image, video | detection | object detection | robust-object-detection | convolution |
| computer vision | image, video | detection | object detection | robust-object-detection | softmax |
| computer vision | image, video | detection | object detection | robust-object-detection | faster-r-cnn |
| computer vision | image, video | detection | object detection | robust-object-detection | rpn |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | deeplabv3 |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | dilated-convolution |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | relu6 |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | average-pooling |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | rmsprop |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | depthwise-separable-convolution |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | aspp |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | depthwise-convolution |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | residual-connection |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | pointwise-convolution |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | residual-block |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | convolution |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | weight-decay |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | mobilenetv2 |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | 1x1-convolution |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | relu |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | spatial-pyramid-pooling |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | inverted-residual-block |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | dropout |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | batch-normalization |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | convolution |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | residual-block |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | max-pooling |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | weight-decay |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | 1x1-convolution |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | relu |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | he-initialization |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | batch-normalization |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | step-decay |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | randomresizedcrop |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | sgd-with-momentum |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | resnet |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | average-pooling |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | global-average-pooling |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | randomhorizontalflip |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | residual-connection |
| computer vision | image, video | classification | medical classification | retinal-oct-disease-classification | bottleneck-residual-block |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | sgd-with-momentum |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | deeplab |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | feedforward-network |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | crf |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | dense-connections |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | softmax |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | vgg |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | max-pooling |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | weight-decay |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | relu |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | dropout |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | softmax |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | max-pooling |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | fire-module |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | relu |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | dropout |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | xavier-initialization |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | residual-connection |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | squeezenet |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | average-pooling |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | espnet |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | dilated-convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | average-pooling |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | dense-connections |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | residual-connection |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | sigmoid-activation |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | strided-eesp |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | pointwise-convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | espnetv2 |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | softmax |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | dropout |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | randomresizedcrop |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | esp |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | lstm |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | hierarchical-feature-fusion |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | randomhorizontalflip |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | concatenated-skip-connection |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | eesp |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | depthwise-separable-convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | cyclical-learning-rate-policy |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | depthwise-convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | tanh-activation |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | eru |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | sgd |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | prelu |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | depthwise-dilated-separable-convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | groupwise-point-convolution |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | he-initialization |
| computer vision | image, video | segmentation | semantic segmentation | real-time-semantic-segmentation | batch-normalization |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | dilated-convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | roi-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | fpn |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | softmax |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | faster-r-cnn |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | 1x1-convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | rpn |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | rpn |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | dense-connections |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | roi-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | vgg-16 |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | softmax |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | max-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | vgg |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | faster-r-cnn |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | relu |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | dropout |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | roi-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | softmax |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | faster-r-cnn |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | rpn |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | svm |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | ssd |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | 1x1-convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | non-maximum-suppression |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | tanh-activation |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | lstm |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | rpn |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | sigmoid-activation |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | roi-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | softmax |
| computer vision | image, video | autonomous vehicle | autonomous car detection | pedestrian-detection | faster-r-cnn |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | googlenet |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | average-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | dense-connections |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | inception-module |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | softmax |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | local-response-normalization |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | max-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | 1x1-convolution |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | relu |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | dropout |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | auxiliary-classifier |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | residual-block |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | max-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | weight-decay |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | 1x1-convolution |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | relu |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | he-initialization |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | batch-normalization |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | step-decay |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | randomresizedcrop |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | sgd-with-momentum |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | resnet |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | average-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | global-average-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | randomhorizontalflip |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | residual-connection |
| computer vision | image, video | autonomous vehicle | autonomous car recognition | pedestrian-attribute-recognition | bottleneck-residual-block |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | yolov2 |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | average-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | global-average-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | softmax |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | max-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | darknet-19 |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | 1x1-convolution |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | batch-normalization |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | rpn |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | segnet |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | relu |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | he-initialization |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | batch-normalization |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | softmax |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | max-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | tanh-activation |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | lstm |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | sigmoid-activation |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | ssd |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | 1x1-convolution |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | non-maximum-suppression |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | global-average-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | softmax |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | max-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | 1x1-convolution |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | fire-module |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | relu |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | dropout |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | xavier-initialization |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | residual-connection |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | squeezenet |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | average-pooling |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | focal-loss |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | carla |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | cycle-consistency-loss |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | gan |
| computer vision | image, video | autonomous vehicle | autonomous car driving | autonomous-driving | carla |
| computer vision | image, video | detection | image detection | curved-text-detection | rpn |
| computer vision | image, video | detection | image detection | curved-text-detection | r-fcn |
| computer vision | image, video | detection | image detection | curved-text-detection | roi-pooling |
| computer vision | image, video | detection | image detection | curved-text-detection | convolution |
| computer vision | image, video | detection | image detection | curved-text-detection | softmax |
| computer vision | image, video | detection | image detection | curved-text-detection | position-sensitive-roi-pooling |
| computer vision | image, video | detection | image detection | curved-text-detection | faster-r-cnn |
| computer vision | image, video | detection | image detection | defect-detection | roi-pooling |
| computer vision | image, video | detection | image detection | defect-detection | convolution |
| computer vision | image, video | detection | image detection | defect-detection | softmax |
| computer vision | image, video | detection | image detection | defect-detection | faster-r-cnn |
| computer vision | image, video | detection | image detection | defect-detection | rpn |
| computer vision | image, video | detection | image detection | face-detection | roi-pooling |
| computer vision | image, video | detection | image detection | face-detection | convolution |
| computer vision | image, video | detection | image detection | face-detection | softmax |
| computer vision | image, video | detection | image detection | face-detection | faster-r-cnn |
| computer vision | image, video | detection | image detection | face-detection | rpn |
| computer vision | image, video | detection | image detection | face-detection | softmax |
| computer vision | image, video | detection | image detection | face-detection | roi-pooling |
| computer vision | image, video | detection | image detection | face-detection | convolution |
| computer vision | image, video | detection | image detection | face-detection | softmax |
| computer vision | image, video | detection | image detection | face-detection | faster-r-cnn |
| computer vision | image, video | detection | image detection | face-detection | rpn |
| computer vision | image, video | detection | image detection | face-model | softmax |
| computer vision | image, video | recognition | image recognition | face-recognition | knowledge-distillation |
| computer vision | image, video | verification | image verification | face-verification | softmax |
| computer vision | image, video | verification | image detection | few-shot-object-detection | convolution |
| computer vision | image, video | verification | image detection | few-shot-object-detection | ssd |
| computer vision | image, video | verification | image detection | few-shot-object-detection | 1x1-convolution |
| computer vision | image, video | verification | image detection | few-shot-object-detection | non-maximum-suppression |
| computer vision | image, video | verification | image detection | few-shot-object-detection | triplet-loss |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | roi-align |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | convolution |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | softmax |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | residual-block |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | max-pooling |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | 1x1-convolution |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | resnext |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | relu |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | he-initialization |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | batch-normalization |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | mask-r-cnn |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | resnet |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | average-pooling |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | global-average-pooling |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | resnext-block |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | grouped-convolution |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | residual-connection |
| computer vision | image, video | segmentation | 3d segmentation | 3d-instance-segmentation-1 | bottleneck-residual-block |
| computer vision | image, video | autonomous vehicle | autonomous car navigation | autonomous-navigation | gan |
| computer vision | image, video | autonomous vehicle | autonomous car navigation | autonomous-navigation | carla |
| computer vision | image, video | detection | image detection | fingertip-detection | roi-pooling |
| computer vision | image, video | detection | image detection | fingertip-detection | convolution |
| computer vision | image, video | detection | image detection | fingertip-detection | softmax |
| computer vision | image, video | detection | image detection | fingertip-detection | faster-r-cnn |
| computer vision | image, video | detection | image detection | fingertip-detection | rpn |
| computer vision | image, video | detection | video detection | fish-detection | roi-pooling |
| computer vision | image, video | detection | video detection | fish-detection | convolution |
| computer vision | image, video | detection | video detection | fish-detection | softmax |
| computer vision | image, video | detection | video detection | fish-detection | faster-r-cnn |
| computer vision | image, video | detection | video detection | fish-detection | rpn |
| computer vision | image, video | detection | image / video detection | hand-detection | roi-pooling |
| computer vision | image, video | detection | image / video detection | hand-detection | convolution |
| computer vision | image, video | detection | image / video detection | hand-detection | softmax |
| computer vision | image, video | detection | image / video detection | hand-detection | faster-r-cnn |
| computer vision | image, video | detection | image / video detection | hand-detection | rpn |
| computer vision | image, video | detection | image / video segmentation | hand-segmentation | roi-pooling |
| computer vision | image, video | detection | image / video segmentation | hand-segmentation | convolution |
| computer vision | image, video | detection | image / video segmentation | hand-segmentation | softmax |
| computer vision | image, video | detection | image / video segmentation | hand-segmentation | faster-r-cnn |
| computer vision | image, video | detection | image / video segmentation | hand-segmentation | rpn |
| computer vision | image, video | detection | image / video segmentation | human-instance-segmentation | roi-align |
| computer vision | image, video | detection | image / video segmentation | human-instance-segmentation | convolution |
| computer vision | image, video | detection | image / video segmentation | human-instance-segmentation | softmax |
| computer vision | image, video | detection | image / video detection | fine-grained-action-detection | tanh-activation |
| computer vision | image, video | detection | image / video detection | fine-grained-action-detection | lstm |
| computer vision | image, video | detection | image / video detection | fine-grained-action-detection | sigmoid-activation |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | roi-align |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | residual-block |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | resnext |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | he-initialization |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | batch-normalization |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | mask-r-cnn |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | resnet |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | resnext-block |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | human-part-segmentation | bottleneck-residual-block |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | convolution |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | residual-block |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | max-pooling |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | weight-decay |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | 1x1-convolution |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | relu |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | he-initialization |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | batch-normalization |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | step-decay |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | randomresizedcrop |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | sgd-with-momentum |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | resnet |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | average-pooling |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | global-average-pooling |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | randomhorizontalflip |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | residual-connection |
| computer vision | image, video | conversion | image conversion | image-to-image-translation | bottleneck-residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | non-maximum-suppression |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-align |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | weight-decay |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | step-decay |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | batch-normalization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | fpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | sgd-with-momentum |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dilated-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dilated-bottleneck-with-projection-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | rpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | randomhorizontalflip |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dilated-bottleneck-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | faster-r-cnn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | detnet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | non-local-operation |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | embedded-dot-product-affinity |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | weight-decay |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnext |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | he-initialization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | concatenation-affinity |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | batch-normalization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | sgd-with-momentum |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | embedded-gaussian-affinity |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnext-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | bottleneck-residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | non-local-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-align |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnext-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | bottleneck-residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | adaptive-feature-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | bottom-up-path-augmentation |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-align |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | weight-decay |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnext |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | panet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | he-initialization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | batch-normalization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | sgd-with-momentum |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | fpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | pafpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | rpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dense-connections |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | mask-r-cnn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-align |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-align |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnext |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | he-initialization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | batch-normalization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | mask-r-cnn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnext-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | bottleneck-residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | he-initialization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | batch-normalization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | bottleneck-residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dilated-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | crf |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | selective-search |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | deepmask |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dense-connections |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | vgg |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dropout |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | fast-r-cnn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnext-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | bottleneck-residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnext |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | he-initialization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | batch-normalization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | rpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | mask-r-cnn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-align |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | faster-r-cnn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | he-initialization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | batch-normalization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | deformable-roi-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | sgd-with-momentum |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | rpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | faster-r-cnn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | deformable-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | bottleneck-residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | deformable-convnets |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-align |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | weight-decay |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | mask-r-cnn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | non-maximum-suppression |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | ccnet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | non-local-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | non-local-operation |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dense-connections |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | mobilenetv1 |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | channel-shuffle |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | depthwise-separable-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | depthwise-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | bottleneck-residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | pointwise-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | shufflenet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | shufflenet-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | mobilenetv2 |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | groupwise-point-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | he-initialization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | inverted-residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | batch-normalization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | fpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dilated-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dilated-bottleneck-with-projection-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | rpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dilated-bottleneck-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | position-sensitive-roi-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | faster-r-cnn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | detnet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | ssd |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | non-maximum-suppression |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | focal-loss |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | r-fcn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | retinanet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnext |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | he-initialization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | batch-normalization |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | fpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | global-convolutional-network |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | rpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | dense-connections |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | senet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | deformable-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | bottleneck-residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | soft-nms |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | sigmoid-activation |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | bottom-up-path-augmentation |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | squeeze-and-excitation-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | htc |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | roi-align |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | cascade-r-cnn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnet |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | pafpn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | precise-roi-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | cascade-mask-r-cnn |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | resnext-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | residual-block |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | instance-segmentation | vgg-16 |
| computer vision | image, video | segmentation | image segmentation | interactive-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | interactive-segmentation | fcn |
| computer vision | image, video | segmentation | image segmentation | interactive-segmentation | max-pooling |
| computer vision | image, video | detection | image detection | keypoint-detection | convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | residual-block |
| computer vision | image, video | detection | image detection | keypoint-detection | max-pooling |
| computer vision | image, video | detection | image detection | keypoint-detection | non-local-operation |
| computer vision | image, video | detection | image detection | keypoint-detection | embedded-dot-product-affinity |
| computer vision | image, video | detection | image detection | keypoint-detection | weight-decay |
| computer vision | image, video | detection | image detection | keypoint-detection | 1x1-convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | resnext |
| computer vision | image, video | detection | image detection | keypoint-detection | relu |
| computer vision | image, video | detection | image detection | keypoint-detection | he-initialization |
| computer vision | image, video | detection | image detection | keypoint-detection | concatenation-affinity |
| computer vision | image, video | detection | image detection | keypoint-detection | batch-normalization |
| computer vision | image, video | detection | image detection | keypoint-detection | sgd-with-momentum |
| computer vision | image, video | detection | image detection | keypoint-detection | resnet |
| computer vision | image, video | detection | image detection | keypoint-detection | embedded-gaussian-affinity |
| computer vision | image, video | detection | image detection | keypoint-detection | average-pooling |
| computer vision | image, video | detection | image detection | keypoint-detection | global-average-pooling |
| computer vision | image, video | detection | image detection | keypoint-detection | resnext-block |
| computer vision | image, video | detection | image detection | keypoint-detection | grouped-convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | residual-connection |
| computer vision | image, video | detection | image detection | keypoint-detection | bottleneck-residual-block |
| computer vision | image, video | detection | image detection | keypoint-detection | non-local-block |
| computer vision | image, video | detection | image detection | keypoint-detection | roi-align |
| computer vision | image, video | detection | image detection | keypoint-detection | convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | softmax |
| computer vision | image, video | detection | image detection | keypoint-detection | roi-align |
| computer vision | image, video | detection | image detection | keypoint-detection | convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | softmax |
| computer vision | image, video | detection | image detection | keypoint-detection | residual-block |
| computer vision | image, video | detection | image detection | keypoint-detection | max-pooling |
| computer vision | image, video | detection | image detection | keypoint-detection | 1x1-convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | resnext |
| computer vision | image, video | detection | image detection | keypoint-detection | relu |
| computer vision | image, video | detection | image detection | keypoint-detection | he-initialization |
| computer vision | image, video | detection | image detection | keypoint-detection | batch-normalization |
| computer vision | image, video | detection | image detection | keypoint-detection | mask-r-cnn |
| computer vision | image, video | detection | image detection | keypoint-detection | resnet |
| computer vision | image, video | detection | image detection | keypoint-detection | average-pooling |
| computer vision | image, video | detection | image detection | keypoint-detection | global-average-pooling |
| computer vision | image, video | detection | image detection | keypoint-detection | resnext-block |
| computer vision | image, video | detection | image detection | keypoint-detection | grouped-convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | residual-connection |
| computer vision | image, video | detection | image detection | keypoint-detection | bottleneck-residual-block |
| computer vision | image, video | detection | image detection | keypoint-detection | fpn |
| computer vision | image, video | detection | image detection | keypoint-detection | mask-r-cnn |
| computer vision | image, video | detection | image detection | keypoint-detection | rpn |
| computer vision | image, video | detection | image detection | keypoint-detection | roi-pooling |
| computer vision | image, video | detection | image detection | keypoint-detection | roi-align |
| computer vision | image, video | detection | image detection | keypoint-detection | convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | softmax |
| computer vision | image, video | detection | image detection | keypoint-detection | faster-r-cnn |
| computer vision | image, video | detection | image detection | keypoint-detection | 1x1-convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | resnet |
| computer vision | image, video | detection | image detection | keypoint-detection | average-pooling |
| computer vision | image, video | detection | image detection | keypoint-detection | dense-connections |
| computer vision | image, video | detection | image detection | keypoint-detection | global-average-pooling |
| computer vision | image, video | detection | image detection | keypoint-detection | mobilenetv1 |
| computer vision | image, video | detection | image detection | keypoint-detection | channel-shuffle |
| computer vision | image, video | detection | image detection | keypoint-detection | depthwise-separable-convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | depthwise-convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | grouped-convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | residual-connection |
| computer vision | image, video | detection | image detection | keypoint-detection | bottleneck-residual-block |
| computer vision | image, video | detection | image detection | keypoint-detection | pointwise-convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | softmax |
| computer vision | image, video | detection | image detection | keypoint-detection | convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | residual-block |
| computer vision | image, video | detection | image detection | keypoint-detection | shufflenet |
| computer vision | image, video | detection | image detection | keypoint-detection | max-pooling |
| computer vision | image, video | detection | image detection | keypoint-detection | shufflenet-block |
| computer vision | image, video | detection | image detection | keypoint-detection | 1x1-convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | mobilenetv2 |
| computer vision | image, video | detection | image detection | keypoint-detection | relu |
| computer vision | image, video | detection | image detection | keypoint-detection | groupwise-point-convolution |
| computer vision | image, video | detection | image detection | keypoint-detection | he-initialization |
| computer vision | image, video | detection | image detection | keypoint-detection | inverted-residual-block |
| computer vision | image, video | detection | image detection | keypoint-detection | batch-normalization |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | convolution |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | fpn |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | convolution |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | focal-loss |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | 1x1-convolution |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | retinanet |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | residual-connection |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | layer-normalization |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | dense-connections |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | label-smoothing |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | transformer |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | scaled |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | softmax |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | position-wise-feed-forward-layer |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | multi-head-attention |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | adam |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | relu |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | absolute-position-encodings |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | dropout |
| computer vision | image, video | detection | image detection | object-detection-in-aerial-images | bpe |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | roi-align |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | convolution |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | softmax |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | residual-block |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | max-pooling |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | 1x1-convolution |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | resnext |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | relu |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | he-initialization |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | batch-normalization |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | mask-r-cnn |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | resnet |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | average-pooling |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | global-average-pooling |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | resnext-block |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | grouped-convolution |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | residual-connection |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | bottleneck-residual-block |
| computer vision | image, video | segmentation | image segmentation | panoptic-segmentation | crf |
| computer vision | image, video | recognition | image recognition | person-re-identification | deeplabv3 |
| computer vision | image, video | recognition | image recognition | person-re-identification | dilated-convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | relu6 |
| computer vision | image, video | recognition | image recognition | person-re-identification | average-pooling |
| computer vision | image, video | recognition | image recognition | person-re-identification | rmsprop |
| computer vision | image, video | recognition | image recognition | person-re-identification | depthwise-separable-convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | aspp |
| computer vision | image, video | recognition | image recognition | person-re-identification | depthwise-convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | residual-connection |
| computer vision | image, video | recognition | image recognition | person-re-identification | pointwise-convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | residual-block |
| computer vision | image, video | recognition | image recognition | person-re-identification | convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | weight-decay |
| computer vision | image, video | recognition | image recognition | person-re-identification | mobilenetv2 |
| computer vision | image, video | recognition | image recognition | person-re-identification | 1x1-convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | relu |
| computer vision | image, video | recognition | image recognition | person-re-identification | spatial-pyramid-pooling |
| computer vision | image, video | recognition | image recognition | person-re-identification | inverted-residual-block |
| computer vision | image, video | recognition | image recognition | person-re-identification | dropout |
| computer vision | image, video | recognition | image recognition | person-re-identification | batch-normalization |
| computer vision | image, video | recognition | image recognition | person-re-identification | average-pooling |
| computer vision | image, video | recognition | image recognition | person-re-identification | rpn |
| computer vision | image, video | recognition | image recognition | person-re-identification | dense-connections |
| computer vision | image, video | recognition | image recognition | person-re-identification | alexnet |
| computer vision | image, video | recognition | image recognition | person-re-identification | global-average-pooling |
| computer vision | image, video | recognition | image recognition | person-re-identification | roi-pooling |
| computer vision | image, video | recognition | image recognition | person-re-identification | channel-shuffle |
| computer vision | image, video | recognition | image recognition | person-re-identification | faster-r-cnn |
| computer vision | image, video | recognition | image recognition | person-re-identification | residual-connection |
| computer vision | image, video | recognition | image recognition | person-re-identification | pointwise-convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | softmax |
| computer vision | image, video | recognition | image recognition | person-re-identification | local-response-normalization |
| computer vision | image, video | recognition | image recognition | person-re-identification | shufflenet-block |
| computer vision | image, video | recognition | image recognition | person-re-identification | weight-decay |
| computer vision | image, video | recognition | image recognition | person-re-identification | 1x1-convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | dropout |
| computer vision | image, video | recognition | image recognition | person-re-identification | randomresizedcrop |
| computer vision | image, video | recognition | image recognition | person-re-identification | randomhorizontalflip |
| computer vision | image, video | recognition | image recognition | person-re-identification | depthwise-convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | grouped-convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | shufflenet |
| computer vision | image, video | recognition | image recognition | person-re-identification | max-pooling |
| computer vision | image, video | recognition | image recognition | person-re-identification | relu |
| computer vision | image, video | recognition | image recognition | person-re-identification | step-decay |
| computer vision | image, video | recognition | image recognition | person-re-identification | batch-normalization |
| computer vision | image, video | recognition | image recognition | person-re-identification | random-erasing |
| computer vision | image, video | recognition | image recognition | person-re-identification | convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | residual-block |
| computer vision | image, video | recognition | image recognition | person-re-identification | max-pooling |
| computer vision | image, video | recognition | image recognition | person-re-identification | weight-decay |
| computer vision | image, video | recognition | image recognition | person-re-identification | 1x1-convolution |
| computer vision | image, video | recognition | image recognition | person-re-identification | relu |
| computer vision | image, video | recognition | image recognition | person-re-identification | he-initialization |
| computer vision | image, video | recognition | image recognition | person-re-identification | batch-normalization |
| computer vision | image, video | recognition | image recognition | person-re-identification | step-decay |
| computer vision | image, video | recognition | image recognition | person-re-identification | randomresizedcrop |
| computer vision | image, video | recognition | image recognition | person-re-identification | sgd-with-momentum |
| computer vision | image, video | recognition | image recognition | person-re-identification | resnet |
| computer vision | image, video | recognition | image recognition | person-re-identification | average-pooling |
| computer vision | image, video | recognition | image recognition | person-re-identification | global-average-pooling |
| computer vision | image, video | recognition | image recognition | person-re-identification | randomhorizontalflip |
| computer vision | image, video | recognition | image recognition | person-re-identification | residual-connection |
| computer vision | image, video | recognition | image recognition | person-re-identification | bottleneck-residual-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | residual-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | max-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | non-local-operation |
| computer vision | image, video | recognition | image recognition | pose-estimation | embedded-dot-product-affinity |
| computer vision | image, video | recognition | image recognition | pose-estimation | weight-decay |
| computer vision | image, video | recognition | image recognition | pose-estimation | 1x1-convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | resnext |
| computer vision | image, video | recognition | image recognition | pose-estimation | relu |
| computer vision | image, video | recognition | image recognition | pose-estimation | he-initialization |
| computer vision | image, video | recognition | image recognition | pose-estimation | concatenation-affinity |
| computer vision | image, video | recognition | image recognition | pose-estimation | batch-normalization |
| computer vision | image, video | recognition | image recognition | pose-estimation | sgd-with-momentum |
| computer vision | image, video | recognition | image recognition | pose-estimation | resnet |
| computer vision | image, video | recognition | image recognition | pose-estimation | embedded-gaussian-affinity |
| computer vision | image, video | recognition | image recognition | pose-estimation | average-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | global-average-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | resnext-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | grouped-convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | residual-connection |
| computer vision | image, video | recognition | image recognition | pose-estimation | bottleneck-residual-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | non-local-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | roi-align |
| computer vision | image, video | recognition | image recognition | pose-estimation | convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | softmax |
| computer vision | image, video | recognition | image recognition | pose-estimation | mask-r-cnn |
| computer vision | image, video | recognition | image recognition | pose-estimation | roi-align |
| computer vision | image, video | recognition | image recognition | pose-estimation | convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | softmax |
| computer vision | image, video | recognition | image recognition | pose-estimation | resnet |
| computer vision | image, video | recognition | image recognition | pose-estimation | average-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | dense-connections |
| computer vision | image, video | recognition | image recognition | pose-estimation | alexnet |
| computer vision | image, video | recognition | image recognition | pose-estimation | global-average-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | grouped-convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | residual-connection |
| computer vision | image, video | recognition | image recognition | pose-estimation | bottleneck-residual-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | softmax |
| computer vision | image, video | recognition | image recognition | pose-estimation | local-response-normalization |
| computer vision | image, video | recognition | image recognition | pose-estimation | residual-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | max-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | 1x1-convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | relu |
| computer vision | image, video | recognition | image recognition | pose-estimation | dropout |
| computer vision | image, video | recognition | image recognition | pose-estimation | he-initialization |
| computer vision | image, video | recognition | image recognition | pose-estimation | batch-normalization |
| computer vision | image, video | recognition | image recognition | pose-estimation | roi-align |
| computer vision | image, video | recognition | image recognition | pose-estimation | convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | softmax |
| computer vision | image, video | recognition | image recognition | pose-estimation | residual-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | max-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | 1x1-convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | resnext |
| computer vision | image, video | recognition | image recognition | pose-estimation | relu |
| computer vision | image, video | recognition | image recognition | pose-estimation | he-initialization |
| computer vision | image, video | recognition | image recognition | pose-estimation | batch-normalization |
| computer vision | image, video | recognition | image recognition | pose-estimation | mask-r-cnn |
| computer vision | image, video | recognition | image recognition | pose-estimation | resnet |
| computer vision | image, video | recognition | image recognition | pose-estimation | average-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | global-average-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | resnext-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | grouped-convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | residual-connection |
| computer vision | image, video | recognition | image recognition | pose-estimation | bottleneck-residual-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | residual-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | softmax |
| computer vision | image, video | recognition | image recognition | pose-estimation | max-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | weight-decay |
| computer vision | image, video | recognition | image recognition | pose-estimation | 1x1-convolution |
| computer vision | image, video | recognition | image recognition | pose-estimation | relu |
| computer vision | image, video | recognition | image recognition | pose-estimation | he-initialization |
| computer vision | image, video | recognition | image recognition | pose-estimation | xavier-initialization |
| computer vision | image, video | recognition | image recognition | pose-estimation | step-decay |
| computer vision | image, video | recognition | image recognition | pose-estimation | batch-normalization |
| computer vision | image, video | recognition | image recognition | pose-estimation | sgd-with-momentum |
| computer vision | image, video | recognition | image recognition | pose-estimation | resnet |
| computer vision | image, video | recognition | image recognition | pose-estimation | rpn |
| computer vision | image, video | recognition | image recognition | pose-estimation | average-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | global-average-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | roi-pooling |
| computer vision | image, video | recognition | image recognition | pose-estimation | faster-r-cnn |
| computer vision | image, video | recognition | image recognition | pose-estimation | rmsprop |
| computer vision | image, video | recognition | image recognition | pose-estimation | bottleneck-residual-block |
| computer vision | image, video | recognition | image recognition | pose-estimation | residual-connection |
| computer vision | image, video | recognition | image recognition | pose-estimation | autoencoder |
| computer vision | image, video | recognition | image recognition | pose-estimation | sparse-autoencoder |
| computer vision | image, video | recognition | image recognition | pose-estimation | svm |
| computer vision | image, video | recognition | image recognition | pose-estimation | vgg-16 |
| computer vision | image, video | generation | video generation | video-retrieval | yolov2 |
| computer vision | image, video | generation | video generation | video-retrieval | average-pooling |
| computer vision | image, video | generation | video generation | video-retrieval | global-average-pooling |
| computer vision | image, video | generation | video generation | video-retrieval | convolution |
| computer vision | image, video | generation | video generation | video-retrieval | softmax |
| computer vision | image, video | generation | video generation | video-retrieval | max-pooling |
| computer vision | image, video | generation | video generation | video-retrieval | darknet-19 |
| computer vision | image, video | generation | video generation | video-retrieval | 1x1-convolution |
| computer vision | image, video | generation | video generation | video-retrieval | batch-normalization |
| computer vision | image, video | segmentation | video segmentation | unsupervised-video-object-segmentation | tanh-activation |
| computer vision | image, video | segmentation | video segmentation | unsupervised-video-object-segmentation | convolution |
| computer vision | image, video | segmentation | video segmentation | unsupervised-video-object-segmentation | dilated-convolution |
| computer vision | image, video | segmentation | video segmentation | unsupervised-video-object-segmentation | sigmoid-activation |
| computer vision | image, video | segmentation | video segmentation | unsupervised-video-object-segmentation | convlstm |
| computer vision | image, video | detection | object-detection | object-localization | convolution |
| computer vision | image, video | detection | object-detection | object-localization | fcn |
| computer vision | image, video | detection | object-detection | object-localization | max-pooling |
| computer vision | image, video | detection | object-detection | object-localization | global-average-pooling |
| computer vision | image, video | detection | object-detection | object-localization | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | object-localization | softmax |
| computer vision | image, video | detection | object-detection | object-localization | convolution |
| computer vision | image, video | detection | object-detection | object-localization | max-pooling |
| computer vision | image, video | detection | object-detection | object-localization | 1x1-convolution |
| computer vision | image, video | detection | object-detection | object-localization | fire-module |
| computer vision | image, video | detection | object-detection | object-localization | relu |
| computer vision | image, video | detection | object-detection | object-localization | dropout |
| computer vision | image, video | detection | object-detection | object-localization | xavier-initialization |
| computer vision | image, video | detection | object-detection | object-localization | residual-connection |
| computer vision | image, video | detection | object-detection | object-localization | squeezenet |
| computer vision | image, video | detection | object-detection | object-localization | ssd |
| computer vision | image, video | detection | object-detection | object-localization | average-pooling |
| computer vision | image, video | detection | object-detection | object-localization | yolov2 |
| computer vision | image, video | detection | object-detection | object-localization | average-pooling |
| computer vision | image, video | detection | object-detection | object-localization | global-average-pooling |
| computer vision | image, video | detection | object-detection | object-localization | convolution |
| computer vision | image, video | detection | object-detection | object-localization | softmax |
| computer vision | image, video | detection | object-detection | object-localization | max-pooling |
| computer vision | image, video | detection | object-detection | object-localization | darknet-19 |
| computer vision | image, video | detection | object-detection | object-localization | 1x1-convolution |
| computer vision | image, video | detection | object-detection | object-localization | batch-normalization |
| computer vision | image, video | detection | object-detection | object-localization | roi-pooling |
| computer vision | image, video | detection | object-detection | object-localization | vgg-16 |
| computer vision | image, video | detection | object-detection | object-localization | convolution |
| computer vision | image, video | detection | object-detection | object-localization | softmax |
| computer vision | image, video | detection | object-detection | object-localization | faster-r-cnn |
| computer vision | image, video | detection | object-detection | object-localization | rpn |
| computer vision | image, video | detection | object-detection | object-localization | 1x1-convolution |
| computer vision | image, video | detection | object-detection | object-localization | relu |
| computer vision | image, video | detection | object-detection | object-localization | he-initialization |
| computer vision | image, video | detection | object-detection | object-localization | batch-normalization |
| computer vision | image, video | detection | object-detection | object-localization | resnet |
| computer vision | image, video | detection | object-detection | object-localization | deeplab |
| computer vision | image, video | detection | object-detection | object-localization | dilated-convolution |
| computer vision | image, video | detection | object-detection | object-localization | crf |
| computer vision | image, video | detection | object-detection | object-localization | average-pooling |
| computer vision | image, video | detection | object-detection | object-localization | dense-connections |
| computer vision | image, video | detection | object-detection | object-localization | global-average-pooling |
| computer vision | image, video | detection | object-detection | object-localization | residual-connection |
| computer vision | image, video | detection | object-detection | object-localization | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | object-localization | feedforward-network |
| computer vision | image, video | detection | object-detection | object-localization | convolution |
| computer vision | image, video | detection | object-detection | object-localization | residual-block |
| computer vision | image, video | detection | object-detection | object-localization | max-pooling |
| computer vision | image, video | detection | object-detection | object-localization | 1x1-convolution |
| computer vision | image, video | detection | object-detection | object-localization | relu |
| computer vision | image, video | detection | object-detection | object-localization | he-initialization |
| computer vision | image, video | detection | object-detection | object-localization | batch-normalization |
| computer vision | image, video | detection | object-detection | object-localization | mask-r-cnn |
| computer vision | image, video | detection | object-detection | object-localization | resnet |
| computer vision | image, video | detection | object-detection | object-localization | rpn |
| computer vision | image, video | detection | object-detection | object-localization | average-pooling |
| computer vision | image, video | detection | object-detection | object-localization | global-average-pooling |
| computer vision | image, video | detection | object-detection | object-localization | roi-pooling |
| computer vision | image, video | detection | object-detection | object-localization | faster-r-cnn |
| computer vision | image, video | detection | object-detection | object-localization | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | object-localization | residual-connection |
| computer vision | image, video | detection | object-detection | object-localization | roi-align |
| computer vision | image, video | detection | object-detection | object-localization | vgg-16 |
| computer vision | image, video | detection | object-detection | object-localization | convolution |
| computer vision | image, video | detection | object-detection | object-localization | softmax |
| computer vision | image, video | detection | object-detection | object-localization | residual-block |
| computer vision | image, video | detection | object-detection | object-localization | max-pooling |
| computer vision | image, video | detection | object-detection | object-localization | grid-r-cnn |
| computer vision | image, video | detection | object-detection | object-localization | non-maximum-suppression |
| computer vision | image, video | detection | object-detection | object-localization | convolution |
| computer vision | image, video | detection | object-detection | object-localization | residual-block |
| computer vision | image, video | detection | object-detection | object-localization | max-pooling |
| computer vision | image, video | detection | object-detection | object-localization | resnext |
| computer vision | image, video | detection | object-detection | object-localization | relu |
| computer vision | image, video | detection | object-detection | object-localization | he-initialization |
| computer vision | image, video | detection | object-detection | object-localization | batch-normalization |
| computer vision | image, video | detection | object-detection | object-localization | syncbn |
| computer vision | image, video | detection | object-detection | object-localization | fpn |
| computer vision | image, video | detection | object-detection | object-localization | sgd-with-momentum |
| computer vision | image, video | detection | object-detection | object-localization | dilated-convolution |
| computer vision | image, video | detection | object-detection | object-localization | rpn |
| computer vision | image, video | detection | object-detection | object-localization | average-pooling |
| computer vision | image, video | detection | object-detection | object-localization | global-average-pooling |
| computer vision | image, video | detection | object-detection | object-localization | roi-pooling |
| computer vision | image, video | detection | object-detection | object-localization | faster-r-cnn |
| computer vision | image, video | detection | object-detection | object-localization | residual-connection |
| computer vision | image, video | detection | object-detection | object-localization | bottleneck-residual-block |
| computer vision | image, video | detection | object-detection | object-localization | sigmoid-activation |
| computer vision | image, video | detection | object-detection | object-localization | roi-align |
| computer vision | image, video | detection | object-detection | object-localization | softmax |
| computer vision | image, video | detection | object-detection | object-localization | fcn |
| computer vision | image, video | detection | object-detection | object-localization | weight-decay |
| computer vision | image, video | detection | object-detection | object-localization | 1x1-convolution |
| computer vision | image, video | detection | object-detection | object-localization | resnet |
| computer vision | image, video | detection | object-detection | object-localization | randomhorizontalflip |
| computer vision | image, video | detection | object-detection | object-localization | resnext-block |
| computer vision | image, video | detection | object-detection | object-localization | grouped-convolution |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | roi-align |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | convolution |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | softmax |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | residual-block |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | max-pooling |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | 1x1-convolution |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | resnext |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | relu |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | he-initialization |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | batch-normalization |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | mask-r-cnn |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | resnet |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | average-pooling |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | global-average-pooling |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | resnext-block |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | grouped-convolution |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | residual-connection |
| computer vision | image, video | recognition | image recognition | multi-person-pose-estimation | bottleneck-residual-block |
| computer vision | image, video | classification | image classification | multi-label-image-classification | googlenet |
| computer vision | image, video | classification | image classification | multi-label-image-classification | average-pooling |
| computer vision | image, video | classification | image classification | multi-label-image-classification | dense-connections |
| computer vision | image, video | classification | image classification | multi-label-image-classification | inception-module |
| computer vision | image, video | classification | image classification | multi-label-image-classification | softmax |
| computer vision | image, video | classification | image classification | multi-label-image-classification | local-response-normalization |
| computer vision | image, video | classification | image classification | multi-label-image-classification | convolution |
| computer vision | image, video | classification | image classification | multi-label-image-classification | max-pooling |
| computer vision | image, video | classification | image classification | multi-label-image-classification | 1x1-convolution |
| computer vision | image, video | classification | image classification | multi-label-image-classification | relu |
| computer vision | image, video | classification | image classification | multi-label-image-classification | dropout |
| computer vision | image, video | classification | image classification | multi-label-image-classification | auxiliary-classifier |
| computer vision | image, video | detection | medical detection | medical-object-detection | ran |
| computer vision | image, video | detection | medical detection | medical-object-detection | convolution |
| computer vision | image, video | detection | medical detection | medical-object-detection | max-pooling |
| computer vision | image, video | detection | medical detection | medical-object-detection | relu |
| computer vision | image, video | detection | medical detection | medical-object-detection | u-net |
| computer vision | image, video | detection | medical detection | medical-object-detection | concatenated-skip-connection |
| computer vision | image, video | generation | image generation | image-dehazing | roi-pooling |
| computer vision | image, video | generation | image generation | image-dehazing | convolution |
| computer vision | image, video | generation | image generation | image-dehazing | softmax |
| computer vision | image, video | generation | image generation | image-dehazing | faster-r-cnn |
| computer vision | image, video | generation | image generation | image-dehazing | rpn |
| computer vision | image, video | conversion | image conversion | cross-view-image-to-image-translation | roi-pooling |
| computer vision | image, video | conversion | image conversion | cross-view-image-to-image-translation | convolution |
| computer vision | image, video | conversion | image conversion | cross-view-image-to-image-translation | softmax |
| computer vision | image, video | conversion | image conversion | cross-view-image-to-image-translation | faster-r-cnn |
| computer vision | image, video | conversion | image conversion | cross-view-image-to-image-translation | rpn |
| computer vision | image, video | generation | image generation | object-proposal-generation | sgd-with-momentum |
| computer vision | image, video | generation | image generation | object-proposal-generation | deepmask |
| computer vision | image, video | generation | image generation | object-proposal-generation | dense-connections |
| computer vision | image, video | generation | image generation | object-proposal-generation | convolution |
| computer vision | image, video | generation | image generation | object-proposal-generation | softmax |
| computer vision | image, video | generation | image generation | object-proposal-generation | max-pooling |
| computer vision | image, video | generation | image generation | object-proposal-generation | vgg |
| computer vision | image, video | generation | image generation | object-proposal-generation | weight-decay |
| computer vision | image, video | generation | image generation | object-proposal-generation | 1x1-convolution |
| computer vision | image, video | generation | image generation | object-proposal-generation | relu |
| computer vision | image, video | generation | image generation | object-proposal-generation | dropout |
| computer vision | image, video | generation | image generation | object-proposal-generation | googlenet |
| computer vision | image, video | generation | image generation | object-proposal-generation | average-pooling |
| computer vision | image, video | generation | image generation | object-proposal-generation | dense-connections |
| computer vision | image, video | generation | image generation | object-proposal-generation | inception-module |
| computer vision | image, video | generation | image generation | object-proposal-generation | softmax |
| computer vision | image, video | generation | image generation | object-proposal-generation | local-response-normalization |
| computer vision | image, video | generation | image generation | object-proposal-generation | convolution |
| computer vision | image, video | generation | image generation | object-proposal-generation | max-pooling |
| computer vision | image, video | generation | image generation | object-proposal-generation | svm |
| computer vision | image, video | generation | image generation | object-proposal-generation | 1x1-convolution |
| computer vision | image, video | generation | image generation | object-proposal-generation | relu |
| computer vision | image, video | generation | image generation | object-proposal-generation | dropout |
| computer vision | image, video | generation | image generation | object-proposal-generation | auxiliary-classifier |
| computer vision | image, video | detection | image detection | object-discovery | gan |
| computer vision | image, video | detection | image detection | object-discovery | convolution |
| computer vision | image, video | detection | image detection | object-discovery | svm |
| computer vision | image, video | detection | object-detection | patch-matching | dense-connections |
| computer vision | image, video | detection | object-detection | patch-matching | label-smoothing |
| computer vision | image, video | detection | object-detection | patch-matching | transformer |
| computer vision | image, video | detection | object-detection | patch-matching | multi-head-attention |
| computer vision | image, video | detection | object-detection | patch-matching | residual-connection |
| computer vision | image, video | detection | object-detection | patch-matching | layer-normalization |
| computer vision | image, video | detection | object-detection | patch-matching | scaled |
| computer vision | image, video | detection | object-detection | patch-matching | spatial-transformer |
| computer vision | image, video | detection | object-detection | patch-matching | softmax |
| computer vision | image, video | detection | object-detection | patch-matching | position-wise-feed-forward-layer |
| computer vision | image, video | detection | object-detection | patch-matching | adam |
| computer vision | image, video | detection | object-detection | patch-matching | relu |
| computer vision | image, video | detection | object-detection | patch-matching | absolute-position-encodings |
| computer vision | image, video | detection | object-detection | patch-matching | dropout |
| computer vision | image, video | detection | object-detection | patch-matching | bpe |
| computer vision | image, video | autonomous vehicle | autonomous car detection | visual-tracking | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | visual-tracking | svm |
| computer vision | image, video | autonomous vehicle | autonomous car detection | visual-tracking | svm |
| computer vision | image, video | autonomous vehicle | autonomous car detection | visual-object-tracking | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | object-tracking | convolution |
| computer vision | image, video | autonomous vehicle | autonomous car detection | object-tracking | siamese-network |
| computer vision | image, video | autonomous vehicle | autonomous car detection | object-tracking | convolution |
| expert system | multiple | consult | - | Interpretation, Prediction, Diagnosis, Design, Planning, Monitoring, Debugging, Repair, Instruction, Control | nan |
| graph processing | graph | embedding | graph embedding | graph embedding | deepgg |
| graph processing | graph | embedding | graph embedding | dynamic graph embedding | dyng2g |
| graph processing | graph | embedding | graph embedding | dynamic graph embedding | dygcn |
| graph processing | graph | embedding | graph embedding | dynamic graph embedding | lstm |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | conve |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | kge-hake |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | kbgan |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | seq2rdf |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | mtranse |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | deeppath |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | mmkb |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | hyper |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | mohr |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | multihopkg |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | kge |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | pykeen |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge graph embedding | kge-rl |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | relational-gcn |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | pykg2vec |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | kbgan |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | kbc |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | sme |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | kbi |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | mmkb |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | convkb |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | mkbe |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | tkbc |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | neuralogic |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | kglr |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | stranse |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | gnn-for-ookb |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | fasttext |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | kbi |
| graph processing | graph | reasoning | knowledge representation and reasoning | knowledge base completion | ffd |
| graph processing | graph | reasoning | embedding | structural node embedding | dnr |
| graph processing | graph | reasoning | embedding | structural node embedding | riwalk |
| graph processing | graph | reasoning | embedding | structural node embedding | snore |
| graph processing | graph | embedding | graph embedding | dynamic graph embedding | lstm |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | conve |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | kge-hake |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | kbgan |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | seq2rdf |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | mtranse |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | deeppath |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | mmkb |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | hyper |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | mohr |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | multihopkg |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | kge |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | pykeen |
| graph processing | graph | embedding | graph embedding | knowledge graph embedding | kge-rl |
| graph processing | graph | embedding | embedding | knowledge base completion | relational-gcn |
| graph processing | graph | embedding | embedding | knowledge base completion | pykg2vec |
| graph processing | graph | embedding | embedding | knowledge base completion | kbgan |
| graph processing | graph | embedding | embedding | knowledge base completion | kbc |
| graph processing | graph | embedding | embedding | knowledge base completion | sme |
| graph processing | graph | embedding | embedding | knowledge base completion | kbi |
| graph processing | graph | embedding | embedding | knowledge base completion | mmkb |
| graph processing | graph | embedding | embedding | knowledge base completion | convkb |
| graph processing | graph | embedding | embedding | knowledge base completion | mkbe |
| graph processing | graph | embedding | embedding | knowledge base completion | tkbc |
| graph processing | graph | embedding | embedding | knowledge base completion | neuralogic |
| graph processing | graph | embedding | embedding | knowledge base completion | kglr |
| graph processing | graph | embedding | embedding | knowledge base completion | stranse |
| graph processing | graph | embedding | embedding | knowledge base completion | gnn-for-ookb |
| graph processing | graph | embedding | embedding | knowledge base completion | fasttext |
| graph processing | graph | embedding | embedding | knowledge base completion | kbi |
| graph processing | graph | embedding | embedding | knowledge base completion | ffd |
| graph processing | graph | embedding | embedding | structural node embedding | dnr |
| graph processing | graph | embedding | embedding | structural node embedding | riwalk |
| graph processing | graph | embedding | embedding | structural node embedding | snore |
| graph processing | graph | embedding | embedding | role embedding | nan |
| graph processing | graph | detection | community detection | community detection | communitygan |
| graph processing | graph | detection | community detection | community detection | smoothgensec2 |
| graph processing | graph | detection | community detection | community detection | agc |
| graph processing | graph | detection | community detection | local community detection | nmf |
| graph processing | graph | detection | community detection | local community detection | generative model |
| graph processing | graph | detection | community detection | online community detection | nan |
| graph processing | graph | detection | community detection | dynamic community detection | incnsa |
| graph processing | graph | detection | community detection | dynamic community detection | dyncommphylo |
| graph processing | graph | detection | community detection | dynamic community detection | tmoga |
| graph processing | graph | detection | community partition | network community partition | nmf |
| graph processing | graph | prediction | medical prediction | gene interaction prediction | gne |
| graph processing | graph | prediction | prediction | set to graph prediction | transformer |
| graph processing | graph | prediction | prediction | hyperedge prediction | transformer |
| graph processing | graph | prediction | prediction | hyperedge prediction | hypred_tensorevd |
| graph processing | graph | prediction | prediction | ancestor-descendant prediction | cone |
| graph processing | graph | classification | graph classification | geometric-deep-learning-on-graphs-and | monet |
| graph processing | graph | classification | node classification | geometric-deep-learning-on-graphs-and | monet |
| graph processing | graph | regression | graph regression | geometric-deep-learning-on-graphs-and | monet |
| graph processing | graph | embedding | graph embedding | data-efficient-graph-embedding-learning-for | roi-pooling |
| graph processing | graph | embedding | graph embedding | data-efficient-graph-embedding-learning-for | softmax |
| graph processing | graph | embedding | graph embedding | data-efficient-graph-embedding-learning-for | convolution |
| graph processing | graph | embedding | graph embedding | data-efficient-graph-embedding-learning-for | faster-r-cnn |
| graph processing | graph | embedding | graph embedding | data-efficient-graph-embedding-learning-for | rpn |
| graph processing | graph | embedding | graph embedding | data-efficient-graph-embedding-learning-for | pcb |
| natural language processing | text | language-modelling | attention | deep attention | nan |
| natural language processing | text | classification | document classification | document classification | mpad-path |
| natural language processing | text | classification | document classification | document classification | acnet |
| natural language processing | text | classification | document classification | document classification | approxrepset |
| natural language processing | text | classification | document classification | document classification | kd-lstmreg |
| natural language processing | text | classification | document classification | document classification | rel-rwmd k-nn |
| natural language processing | text | classification | document classification | sentence classification | fe-mlm+span |
| natural language processing | text | classification | document classification | sentence classification | scibert |
| natural language processing | text | classification | document classification | sentence classification | hierarchical neural networks |
| natural language processing | text | classification | document classification | sentence classification | roberta-large |
| natural language processing | text | classification | document classification | cross-lingual document classification | xlmft uda |
| natural language processing | text | classification | document classification | cross-lingual document classification | multifit, pseudo |
| natural language processing | text | classification | document classification | cross-lingual document classification | biinclusion |
| natural language processing | text | classification | document classification | cross-lingual document classification | bilstm |
| natural language processing | text | classification | document classification | document ranking | xlnet |
| natural language processing | text | classification | document classification | document ranking | query-doc robeczech |
| natural language processing | text | classification | document classification | document ranking | roberta-base |
| natural language processing | text | natural language generation | document summarization | multi-document summarization | nan |
| natural language processing | text | natural language generation | document summarization | document summarization | nan |
| natural language processing | text | language-modelling | embedding evaluation | embedding evaluation | nan |
| natural language processing | text | classification | emotion classification | emotion classification | spanemo |
| natural language processing | text | classification | emotion classification | emotion classification | proxemo |
| natural language processing | text | classification | emotion classification | emotion classification | semi-supervision |
| natural language processing | text | classification | emotion classification | emotion classification | mlknn |
| natural language processing | text | classification | emotion classification | emotion classification | bert |
| natural language processing | text | classification | emotion classification | emotion classification | erann-0-4 |
| natural language processing | text | classification | emotion classification | complaint comment classification | nan |
| natural language processing | text | extraction | emotion extraction | emotion cause extraction | rthn |
| natural language processing | text | extraction | emotion extraction | emotion cause extraction | pae-dgl |
| natural language processing | text | extraction | emotion extraction | emotion cause extraction | convms-memnet |
| natural language processing | text | extraction | emotion extraction | multimodal emotion recognition | chfusion |
| natural language processing | text | extraction | emotion extraction | multimodal emotion recognition | bc-lstm |
| natural language processing | text | extraction | emotion extraction | multimodal emotion recognition | pathosnet v2 |
| natural language processing | text | extraction | emotion extraction | multimodal emotion recognition | smplify-x |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | dag-erc+hcl |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | s+page |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | emoberta |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | dag-erc |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | dialoguetrm |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | cesta |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | cog-bart |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | ki-net |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | skaig |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | sumagggin |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | dialoguecrn |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | dialogxl |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | trmsm-att |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | coin |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | pretrained hierarchical transformer |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | cosmic |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | rgat |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | bieru-lc |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | hitrans |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | iterative |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | dialoguegcn |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | ermc-disgcn |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | bif-agru |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | dialoguernn |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | todkat |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | ket |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | vhred |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | icon |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | bc-lstm+att |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | cmn |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | emoberta |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | s+page |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | cog-bart |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | nelec |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | dialoguegcn |
| natural language processing | text | extraction | emotion extraction | emotion recognition in conversation | hitransformer-s |
| natural language processing | text | extraction | emotion extraction | emotion recognition | logisticregression on posteriors of xlsr-wav2vec2.0&bi-lstm+attention |
| natural language processing | text | extraction | emotion extraction | emotion recognition | jukebox (pre-training: calm) |
| natural language processing | text | extraction | emotion extraction | emotion recognition | rgnn |
| natural language processing | text | extraction | emotion extraction | emotion recognition | bihdm |
| natural language processing | text | extraction | emotion extraction | emotion recognition | 4d-ann |
| natural language processing | text | extraction | emotion extraction | emotion cause pair extraction | rankcp |
| natural language processing | text | extraction | emotion extraction | emotion cause pair extraction | ecpe-2d |
| natural language processing | text | extraction | emotion extraction | emotion cause pair extraction | mtnecp |
| natural language processing | text | extraction | emotion extraction | emotion cause pair extraction | e2eecpe |
| natural language processing | text | extraction | emotion extraction | emotion cause pair extraction | inter-ec |
| natural language processing | text | extraction | entity extraction | role-filler entity extraction | tempgen |
| natural language processing | text | extraction | entity extraction | temporal information extraction | catena |
| natural language processing | text | extraction | entity extraction | temporal information extraction | ning et al. |
| natural language processing | text | extraction | entity extraction | event extraction | deepeventmine |
| natural language processing | text | extraction | entity extraction | event extraction | geanet-scibert |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | gcn |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | mrc-for-flat-nested-ner |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | auto-labeled-corpus |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | py-pampo |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | hrl-re |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | multitasking_transformers |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | mt-clinical bert |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | tf-mtrnn |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | evententityextractor |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | ner-diff-paper |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | spextor |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | named-entity-recognition |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | transfer-learning-ner |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | eaten |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | nlpinformationextraction |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | nasa-se |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | sdrn |
| natural language processing | text | extraction | entity extraction | entity extraction using GAN | copymtl |
| natural language processing | text | extraction | entity extraction | binary relation extraction | tempgen |
| natural language processing | text | extraction | entity extraction | dialog relation extraction | bilstm |
| natural language processing | text | extraction | entity extraction | dialog relation extraction | berts |
| natural language processing | text | extraction | entity extraction | relationship extraction | ssan-roberta-large+adaptation |
| natural language processing | text | extraction | entity extraction | relationship extraction | sais-roberta-large |
| natural language processing | text | extraction | entity extraction | relationship extraction | eider-roberta-large |
| natural language processing | text | extraction | entity extraction | relationship extraction | docunet-roberta-large |
| natural language processing | text | extraction | entity extraction | relationship extraction | cgm2ir-robertalarge |
| natural language processing | text | extraction | entity extraction | relationship extraction | atlop-roberta-large |
| natural language processing | text | extraction | entity extraction | relationship extraction | sais-bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | gain-bert-large |
| natural language processing | text | extraction | entity extraction | relationship extraction | e2gre-roberta-large |
| natural language processing | text | extraction | entity extraction | relationship extraction | eider-bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | cgm2ir-bertbase |
| natural language processing | text | extraction | entity extraction | relationship extraction | sire-bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | mrn+bert |
| natural language processing | text | extraction | entity extraction | relationship extraction | atlop + logire |
| natural language processing | text | extraction | entity extraction | relationship extraction | ssan-roberta-large |
| natural language processing | text | extraction | entity extraction | relationship extraction | drn-bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | atlop-bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | gain-bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | gain + logire |
| natural language processing | text | extraction | entity extraction | relationship extraction | jerex-bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | corefroberta-large |
| natural language processing | text | extraction | entity extraction | relationship extraction | ssan-roberta-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | cfer-bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | hetergsan+reconstruction+bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | lsr+bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | glre-xlnet-large |
| natural language processing | text | extraction | entity extraction | relationship extraction | corefbert-large |
| natural language processing | text | extraction | entity extraction | relationship extraction | e2gre-bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | encattagg |
| natural language processing | text | extraction | entity extraction | relationship extraction | mrn |
| natural language processing | text | extraction | entity extraction | relationship extraction | ssan-bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | dual+bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | corefbert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | drn-glove |
| natural language processing | text | extraction | entity extraction | relationship extraction | paths+bilstm-glove |
| natural language processing | text | extraction | entity extraction | relationship extraction | sire-glove |
| natural language processing | text | extraction | entity extraction | relationship extraction | cfer-glove |
| natural language processing | text | extraction | entity extraction | relationship extraction | hin-bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | hetergsan+reconstruction |
| natural language processing | text | extraction | entity extraction | relationship extraction | gain-glove |
| natural language processing | text | extraction | entity extraction | relationship extraction | lsr+glove |
| natural language processing | text | extraction | entity extraction | relationship extraction | two-step+bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | hin-glove |
| natural language processing | text | extraction | entity extraction | relationship extraction | bert-base |
| natural language processing | text | extraction | entity extraction | relationship extraction | greg |
| natural language processing | text | extraction | entity extraction | relationship extraction | docred-bilstm |
| natural language processing | text | extraction | entity extraction | relationship extraction | docred-context-aware |
| natural language processing | text | extraction | entity extraction | relationship extraction | docred-lstm |
| natural language processing | text | extraction | entity extraction | relationship extraction | docred-cnn |
| natural language processing | text | extraction | entity extraction | joint entity and relation extraction | pl-maker |
| natural language processing | text | extraction | entity extraction | joint entity and relation extraction | spn |
| natural language processing | text | extraction | entity extraction | joint entity and relation extraction | rebel |
| natural language processing | text | extraction | entity extraction | joint entity and relation extraction | ours: cross-sentence alb |
| natural language processing | text | extraction | entity extraction | relation mention extraction | nan |
| natural language processing | text | extraction | entity extraction | multi-labeled relation extraction | nan |
| natural language processing | text | extraction | entity extraction | 4-ary relation extraction | tempgen |
| natural language processing | text | extraction | entity extraction | key phrase extraction | wiki+roberta |
| natural language processing | text | extraction | entity extraction | key phrase extraction | ucphrase |
| natural language processing | text | extraction | entity extraction | key phrase extraction | autophrase |
| natural language processing | text | extraction | entity extraction | key phrase extraction | spacy |
| natural language processing | text | extraction | entity extraction | key phrase extraction | pke |
| natural language processing | text | extraction | entity extraction | key phrase extraction | topmine |
| natural language processing | text | extraction | entity extraction | key phrase extraction | stanfordnlp |
| natural language processing | text | extraction | entity extraction | scientific results extraction | axcell |
| natural language processing | text | extraction | entity extraction | scientific results extraction | tdms-ie |
| natural language processing | text | extraction | entity extraction | scientific concept extraction | scibert (active learning) |
| natural language processing | text | extraction | entity extraction | definition extraction | defteval |
| natural language processing | text | extraction | entity extraction | definition extraction | defext |
| natural language processing | text | extraction | entity extraction | definition extraction | definition_extraction |
| natural language processing | text | extraction | entity extraction | definition extraction | semeval-2020-task-6 |
| natural language processing | text | extraction | entity extraction | open information extraction | transformer-capsule |
| natural language processing | text | extraction | entity extraction | open information extraction | attention encoder-decoder nn |
| natural language processing | text | extraction | entity extraction | open information extraction | joint model with recurrent slot label context |
| natural language processing | text | extraction | entity extraction | open information extraction | sf-id(blstm) |
| natural language processing | text | extraction | entity extraction | open information extraction | sf-id |
| natural language processing | text | extraction | entity extraction | open information extraction | stack-propagation(+bert) |
| natural language processing | text | extraction | entity extraction | open information extraction | delta (blstm-crf) |
| natural language processing | text | extraction | entity extraction | open information extraction | capsule-nlu |
| natural language processing | text | extraction | entity extraction | open information extraction | slot-gated blstm with attension |
| natural language processing | text | extraction | entity extraction | open information extraction | joint bert + crf |
| natural language processing | text | extraction | entity extraction | open information extraction | joint bert |
| natural language processing | text | extraction | entity extraction | open information extraction | context encoder |
| natural language processing | text | extraction | entity extraction | open information extraction | gl-gin |
| natural language processing | text | extraction | entity extraction | open information extraction | plain-lstm |
| natural language processing | text | extraction | entity extraction | attribute value extraction | second-best learning and decoding |
| natural language processing | text | extraction | entity extraction | attribute value extraction | seq2seq+bert+flair |
| natural language processing | text | extraction | entity extraction | attribute value extraction | merge and label |
| natural language processing | text | extraction | entity extraction | attribute value extraction | mgner |
| natural language processing | text | extraction | entity extraction | attribute value extraction | biflag |
| natural language processing | text | extraction | entity extraction | attribute value extraction | anchor-region networks |
| natural language processing | text | extraction | entity extraction | attribute value extraction | neural segmental hypergraphs |
| natural language processing | text | extraction | entity extraction | attribute value extraction | neural transition-based model |
| natural language processing | text | extraction | entity extraction | attribute value extraction | neural layered model |
| natural language processing | text | extraction | entity extraction | information extraction | flair embeddings |
| natural language processing | text | extraction | entity extraction | information extraction | char bi-lstm |
| natural language processing | text | extraction | entity extraction | information extraction | cvt + multi-task |
| natural language processing | text | extraction | entity extraction | information extraction | spanrel |
| natural language processing | text | extraction | entity extraction | information extraction | bilstm-lan |
| natural language processing | text | extraction | entity extraction | information extraction | adversarial bi-lstm |
| natural language processing | text | extraction | entity extraction | information extraction | intnet + bilstm-crf |
| natural language processing | text | extraction | entity extraction | information extraction | yang et al. |
| natural language processing | text | extraction | entity extraction | information extraction | blstm-cnn-crf |
| natural language processing | text | extraction | entity extraction | information extraction | s-lstm |
| natural language processing | text | extraction | entity extraction | information extraction | lm-lstm-crf |
| natural language processing | text | extraction | entity extraction | information extraction | ncrf++ |
| natural language processing | text | extraction | entity extraction | information extraction | bi-lstm + lmcost |
| natural language processing | text | extraction | entity extraction | information extraction | feed forward |
| natural language processing | text | extraction | entity extraction | information extraction | bi-lstm |
| natural language processing | text | extraction | entity extraction | information extraction | bi-lstm + charattn |
| natural language processing | text | extraction | entity extraction | information extraction | bi-lstm |
| natural language processing | text | extraction | entity extraction | information extraction | ace |
| natural language processing | text | extraction | entity extraction | information extraction | bilstm-lan |
| natural language processing | text | extraction | entity extraction | information extraction | pretrand |
| natural language processing | text | extraction | entity extraction | information extraction | trankit |
| natural language processing | text | extraction | entity extraction | information extraction | camembert |
| natural language processing | text | extraction | entity extraction | term extraction | pannuke-metrics |
| natural language processing | text | extraction | entity extraction | term extraction | leakage-neutral-learning-for-quoraqp |
| natural language processing | text | extraction | entity extraction | term extraction | paper-debiased-feature-importance |
| natural language processing | text | extraction | entity extraction | term extraction | adp |
| natural language processing | text | extraction | entity extraction | term extraction | ivaps |
| natural language processing | text | extraction | entity extraction | term extraction | mlforhealthlabpub |
| natural language processing | text | extraction | entity extraction | term extraction | ctrl-iwxval |
| natural language processing | text | extraction | entity extraction | term extraction | libtlda |
| natural language processing | text | extraction | entity extraction | term extraction | bqcd |
| natural language processing | text | extraction | entity extraction | term extraction | covshift-skewness |
| natural language processing | text | extraction | entity extraction | term extraction | cci |
| natural language processing | text | extraction | entity extraction | term extraction | deep-counterfactual-networks-with-propensity-dropout |
| natural language processing | text | extraction | entity extraction | term extraction | mlforhealthlabpub |
| natural language processing | text | extraction | entity extraction | term extraction | covshift-skewness |
| natural language processing | text | extraction | entity extraction | term extraction | cci |
| natural language processing | text | extraction | entity extraction | term extraction | mlforhealthlabpub |
| natural language processing | text | extraction | entity extraction | term extraction | facenet-tf |
| natural language processing | text | extraction | entity extraction | term extraction | sar-pu |
| natural language processing | text | extraction | entity extraction | term extraction | site |
| natural language processing | text | extraction | entity extraction | term extraction | dosearch |
| natural language processing | text | extraction | entity extraction | term extraction | homesteads |
| natural language processing | text | extraction | entity extraction | term extraction | adversarial-balancing-based-representation-learning-for-causal-effect-inference |
| natural language processing | text | extraction | entity extraction | term extraction | biasedpulearnig |
| natural language processing | text | extraction | entity extraction | term extraction | g-bert |
| natural language processing | text | extraction | entity extraction | term extraction | neuropathic-pain-diagnosis-simulator |
| natural language processing | text | extraction | entity extraction | term extraction | asymmetric-tri-rec-real |
| natural language processing | text | extraction | entity extraction | term extraction | esam |
| natural language processing | text | extraction | entity extraction | term extraction | non-discrimination-learning-for-text-classification |
| natural language processing | text | extraction | entity extraction | term extraction | ijcai2020-dckm |
| natural language processing | text | extraction | entity extraction | term extraction | 2020ictir-evaluation |
| natural language processing | text | extraction | entity extraction | term extraction | leebounds |
| natural language processing | text | extraction | entity extraction | term extraction | dct-policy |
| natural language processing | text | extraction | entity extraction | term extraction | 2021wsdm-unifying-ltr |
| natural language processing | text | extraction | entity extraction | term extraction | sc-cfr |
| natural language processing | text | extraction | entity extraction | term extraction | matching-with-gans |
| natural language processing | text | extraction | entity extraction | term extraction | mrdr-dl |
| natural language processing | text | extraction | entity extraction | term extraction | aul |
| natural language processing | text | extraction | entity extraction | term extraction | ivg |
| natural language processing | text | extraction | entity extraction | term extraction | rest |
| natural language processing | text | extraction | entity extraction | term extraction | l-marvel |
| natural language processing | text | extraction | entity extraction | term extraction | survtrace |
| natural language processing | text | extraction | entity extraction | term extraction | gradlre |
| natural language processing | text | extraction | entity extraction | term extraction | cfie |
| natural language processing | text | extraction | entity extraction | term extraction | noise-level-causal-identification-additive-noise-models |
| natural language processing | text | extraction | entity extraction | term extraction | aaa |
| natural language processing | text | extraction | entity extraction | term extraction | dsit |
| natural language processing | text | extraction | entity extraction | keyword extraction | phraseformer(bert, exem(ft)) |
| natural language processing | text | extraction | entity extraction | keyword extraction | phraseformer(bert, node2vec) |
| natural language processing | text | extraction | entity extraction | keyword extraction | phraseformer(bert, deepwalk) |
| natural language processing | text | extraction | entity extraction | keyword extraction | frake |
| natural language processing | text | recognition | entity recognition | overlapping mention recognition | overlapping-ner-em18 |
| natural language processing | text | recognition | entity recognition | irregular text recognition | mmocr |
| natural language processing | text | recognition | entity recognition | irregular text recognition | textimagestoolkit |
| natural language processing | text | recognition | entity recognition | irregular text recognition | cvpr20-scatter-text-recognizer |
| natural language processing | text | recognition | entity recognition | irregular text recognition | convolutional-attention-network-for-scene-text-recognition |
| natural language processing | text | recognition | entity recognition | handwritten digit recognition | sign-symmetry |
| natural language processing | text | recognition | entity recognition | handwritten digit recognition | cnn |
| natural language processing | text | recognition | entity recognition | handwriting recognition | akhcrnet |
| natural language processing | text | recognition | entity recognition | handwriting recognition | flor |
| natural language processing | text | recognition | entity recognition | grammatical error correction | cnn seq2seq + fluency boost |
| natural language processing | text | recognition | entity recognition | grammatical error correction | cnn seq2seq + quality estimation |
| natural language processing | text | recognition | entity recognition | grammatical error correction | vernet |
| natural language processing | text | recognition | entity recognition | grammatical error correction | sequence tagging + token-level transformations + two-stage fine-tuning (+bert, roberta, xlnet) |
| natural language processing | text | recognition | entity recognition | table search | a-learned-sorted-table-search-library |
| natural language processing | text | recognition | entity recognition | table search | gtr |
| natural language processing | text | recognition | entity recognition | table search | sigir2020-bert-table-search |
| natural language processing | text | recognition | entity recognition | grammatical error correction | smt + bigru |
| natural language processing | text | recognition | entity recognition | grammatical error correction | lm-critic (unsupervised) |
| natural language processing | text | recognition | entity recognition | nested mention recognition | boningknife |
| natural language processing | text | recognition | entity recognition | optical character recognition | attentionocr_inception-resnet-v2_location |
| natural language processing | text | recognition | entity recognition | optical character recognition | see |
| natural language processing | text | recognition | entity recognition | optical character recognition | street |
| natural language processing | text | recognition | entity recognition | optical character recognition | i2l-nopool |
| natural language processing | text | recognition | entity recognition | optical character recognition | i2l-strips |
| natural language processing | text | recognition | entity recognition | paraphrase identification | xlnet-large |
| natural language processing | text | recognition | entity recognition | paraphrase identification | structbertroberta ensemble |
| natural language processing | text | recognition | entity recognition | paraphrase identification | fnet-large |
| natural language processing | text | recognition | entity recognition | paraphrase identification | realformer |
| natural language processing | text | recognition | entity recognition | paraphrase identification | charformer-tall |
| natural language processing | text | recognition | entity recognition | paraphrase identification | efl |
| natural language processing | text | recognition | entity recognition | paraphrase identification | snorkel metal |
| natural language processing | text | recognition | entity recognition | paraphrase identification | mt-dnn |
| natural language processing | text | recognition | entity recognition | paraphrase identification | spanbert |
| natural language processing | text | recognition | entity recognition | paraphrase identification | tinybert |
| natural language processing | text | recognition | entity recognition | paraphrase identification | ernie |
| natural language processing | text | recognition | entity recognition | paraphrase identification | mfae |
| natural language processing | text | recognition | entity recognition | paraphrase identification | re2 |
| natural language processing | text | recognition | entity recognition | paraphrase identification | mwan |
| natural language processing | text | recognition | entity recognition | paraphrase identification | diin |
| natural language processing | text | recognition | entity recognition | paraphrase identification | msem |
| natural language processing | text | recognition | entity recognition | paraphrase identification | bi-cas-lstm |
| natural language processing | text | recognition | entity recognition | paraphrase identification | pt-decatt |
| natural language processing | text | recognition | entity recognition | paraphrase identification | bimpm |
| natural language processing | text | recognition | entity recognition | paraphrase identification | gensen |
| natural language processing | text | recognition | entity recognition | paraphrase identification | 1-3[0.8pt/2pt] random |
| natural language processing | text | recognition | entity recognition | paraphrase identification | bert-base |
| natural language processing | text | recognition | entity recognition | paraphrase identification | cnn |
| natural language processing | text | recognition | entity recognition | paraphrase identification | par bert base |
| natural language processing | text | recognition | entity recognition | paraphrase identification | structbertroberta ensemble |
| natural language processing | text | recognition | entity recognition | paraphrase identification | tsdae |
| natural language processing | text | recognition | entity recognition | paraphrase identification | robetra base |
| natural language processing | text | recognition | entity recognition | selection bias | deepctr |
| natural language processing | text | retrieval | entity retrieval | information retrieval | hpipubcommon |
| natural language processing | text | retrieval | entity retrieval | information retrieval | hpictall |
| natural language processing | text | retrieval | entity retrieval | information retrieval | tsdae |
| natural language processing | text | retrieval | entity retrieval | information retrieval | bert+concept filter |
| natural language processing | sound, audio | detection | feature detection | hate speech detection | nan |
| natural language processing | sound, audio | detection | feature detection | manner of articulation detection | nan |
| natural language processing | sound, audio | detection | feature detection | deepfake detection | nan |
| natural language processing | sound, audio | detection | feature detection | hate speech detection | nan |
| natural language processing | sound, audio | detection | feature detection | hope speech detection | nan |
| natural language processing | sound, audio | recognition | feature recognition | speech emotion recognition | nan |
| natural language processing | sound, audio | recognition | feature recognition | emotion recognition in conversation | nan |
| natural language processing | sound, audio | recognition | feature recognition | facial emotion recognition | nan |
| natural language processing | sound, audio | recognition | feature recognition | emotion recognition in conversation | nan |
| natural language processing | sound, audio | recognition | feature recognition | facial emotion recognition | nan |
| natural language processing | sound, audio | recognition | feature recognition | emotion cause extraction | nan |
| natural language processing | sound, audio | recognition | feature recognition | emotion cause pair extraction | nan |
| natural language processing | sound, audio | recognition | feature recognition | multimodal emotion recognition | nan |
| natural language processing | sound, audio | recognition | feature recognition | emotion recognition in context | nan |
| natural language processing | sound, audio | recognition | feature recognition | eeg emotion recognition | nan |
| natural language processing | text | reasoning | knowledge representation and reasoning | knowledge graph embedding | nan |
| natural language processing | text | reasoning | knowledge representation and reasoning | graph-to-sequence | nan |
| natural language processing | image | classification | image classification | page stream segmentation | nan |
| natural language processing | text | classification | image classification | learning with noisy labels | cores* |
| natural language processing | text | classification | image classification | learning with noisy labels | divide-mix |
| natural language processing | text | classification | image classification | learning with noisy labels | elr+ |
| natural language processing | text | classification | image classification | learning with noisy labels | cal |
| natural language processing | text | classification | image classification | learning with noisy labels | co-teaching |
| natural language processing | text | classification | image classification | learning with noisy labels | cores |
| natural language processing | text | classification | image classification | learning with noisy labels | elr |
| natural language processing | text | classification | image classification | learning with noisy labels | jocor |
| natural language processing | text | classification | image classification | learning with noisy labels | co-teaching+ |
| natural language processing | text | classification | image classification | learning with noisy labels | negative-ls |
| natural language processing | text | classification | image classification | learning with noisy labels | positive-ls |
| natural language processing | text | classification | image classification | learning with noisy labels | f-div |
| natural language processing | text | classification | image classification | learning with noisy labels | peer loss |
| natural language processing | text | classification | image classification | learning with noisy labels | gce |
| natural language processing | text | classification | image classification | learning with noisy labels | volminnet |
| natural language processing | text | classification | image classification | learning with noisy labels | t-revision |
| natural language processing | text | classification | image classification | learning with noisy labels | forward-t |
| natural language processing | text | classification | image classification | learning with noisy labels | ce |
| natural language processing | text | classification | image classification | learning with noisy labels | backward-t |
| natural language processing | sound, audio | natural language generation | image-text generation | visual dialog | nan |
| natural language processing | text | natural language generation | knowledge-text conversion | kg-to-text generation | nan |
| natural language processing | text | reasoning | knowledge representation and reasoning | kg-to-text generation | nan |
| natural language processing | text | reasoning | knowledge representation and reasoning | kb-to-language generation | nan |
| natural language processing | text | natural language generation | knowledge-text conversion | kb-to-language generation | nan |
| natural language processing | text | reasoning | knowledge representation and reasoning | unsupervised kg-to-text generation | nan |
| natural language processing | text | natural language generation | knowledge-text conversion | unsupervised kg-to-text generation | nan |
| natural language processing | text | learning | learning | weakly supervised data denoising | knodle |
| natural language processing | text | language-modelling | learning | contrastive learning | nan |
| natural language processing | text | language-modelling | learning | dependency grammar induction, constituency grammar induction | nan |
| natural language processing | text | language-modelling | learning | prepositional phrase attachment | nan |
| natural language processing | text | language-modelling | learning | active learning | yolov2 |
| natural language processing | text | language-modelling | learning | active learning | yolov2 |
| natural language processing | text | language-modelling | learning | active learning | rpn |
| natural language processing | text | language-modelling | learning | active learning | rpn |
| natural language processing | text | language-modelling | learning | active learning | average-pooling |
| natural language processing | text | language-modelling | learning | active learning | average-pooling |
| natural language processing | text | language-modelling | learning | active learning | global-average-pooling |
| natural language processing | text | language-modelling | learning | active learning | global-average-pooling |
| natural language processing | text | language-modelling | learning | active learning | roi-pooling |
| natural language processing | text | language-modelling | learning | active learning | roi-pooling |
| natural language processing | text | language-modelling | learning | active learning | convolution |
| natural language processing | text | language-modelling | learning | active learning | convolution |
| natural language processing | text | language-modelling | learning | active learning | softmax |
| natural language processing | text | language-modelling | learning | active learning | softmax |
| natural language processing | text | language-modelling | learning | active learning | faster-r-cnn |
| natural language processing | text | language-modelling | learning | active learning | faster-r-cnn |
| natural language processing | text | language-modelling | learning | active learning | max-pooling |
| natural language processing | text | language-modelling | learning | active learning | max-pooling |
| natural language processing | text | language-modelling | learning | active learning | darknet-19 |
| natural language processing | text | language-modelling | learning | active learning | darknet-19 |
| natural language processing | text | language-modelling | learning | active learning | 1x1-convolution |
| natural language processing | text | language-modelling | learning | active learning | 1x1-convolution |
| natural language processing | text | language-modelling | learning | active learning | fast-r-cnn |
| natural language processing | text | language-modelling | learning | active learning | fast-r-cnn |
| natural language processing | text | language-modelling | learning | active learning | batch-normalization |
| natural language processing | text | language-modelling | learning | active learning | batch-normalization |
| natural language processing | text | language-modelling | learning | unifying-visual-semantic-embeddings-with | tanh-activation |
| natural language processing | text | language-modelling | learning | unifying-visual-semantic-embeddings-with | lstm |
| natural language processing | text | language-modelling | learning | unifying-visual-semantic-embeddings-with | sigmoid-activation |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | espnet |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | dilated-convolution |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | average-pooling |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | dense-connections |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | global-average-pooling |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | residual-connection |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | sigmoid-activation |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | strided-eesp |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | pointwise-convolution |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | espnetv2 |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | softmax |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | 1x1-convolution |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | dropout |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | randomresizedcrop |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | esp |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | lstm |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | hierarchical-feature-fusion |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | randomhorizontalflip |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | concatenated-skip-connection |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | eesp |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | depthwise-separable-convolution |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | cyclical-learning-rate-policy |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | depthwise-convolution |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | grouped-convolution |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | tanh-activation |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | eru |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | sgd |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | prelu |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | convolution |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | depthwise-dilated-separable-convolution |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | groupwise-point-convolution |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | he-initialization |
| natural language processing | text | language-modelling | learning | espnetv2-a-light-weight-power-efficient-and | batch-normalization |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | googlenet |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | lstm |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | average-pooling |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | dense-connections |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | inception-module |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | auxiliary-classifier |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | tanh-activation |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | sigmoid-activation |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | softmax |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | local-response-normalization |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | convolution |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | max-pooling |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | 1x1-convolution |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | relu |
| natural language processing | text | language-modelling | learning | weighted-entropy-based-quantization-for-deep | dropout |
| natural language processing | text | translation | legal translation | legal document translation | nan |
| natural language processing | text | language-modelling | lemmatization | lemmatization | nan |
| natural language processing | text | classification | logic classification | citation latent classification | scibert |
| natural language processing | text | classification | logic classification | citation latent classification | structural-scaffolds |
| natural language processing | text | classification | logic classification | coherence evaluation | rst-ensemble |
| natural language processing | text | classification | logic classification | relation classification | brcnn |
| natural language processing | text | classification | logic classification | relation classification | deepex |
| natural language processing | text | classification | logic classification | relation classification | resattarg |
| natural language processing | text | classification | logic classification | few-shot relation classification | bert-relation-extraction |
| natural language processing | text | classification | logic classification | few-shot relation classification | fewrel |
| natural language processing | text | classification | logic classification | few-shot relation classification | mlman |
| natural language processing | text | classification | logic classification | few-shot relation classification | miml |
| natural language processing | text | classification | logic classification | open intent discovery | cdac+ |
| natural language processing | text | classification | logic classification | open intent discovery | deepaligned |
| natural language processing | text | classification | logic classification | intent classification | roberta-wwm-ext-base |
| natural language processing | text | classification | logic classification | intent classification | partially fine-tuned hubert |
| natural language processing | text | translation | machine translation | multilingual neural machine translation | nan |
| natural language processing | text | translation | machine translation | multimodal machine translation | nan |
| natural language processing | text | translation | machine translation | machine translation | nan |
| natural language processing | text | translation | machine translation | transliteration | nan |
| natural language processing | text | translation | machine translation | automatic post-editing | nan |
| natural language processing | text | translation | machine translation | bilingual lexicon induction | nan |
| natural language processing | text | translation | machine translation | unsupervised machine translation | nan |
| natural language processing | text | translation | machine translation | low-resource neural machine translation | nan |
| natural language processing | text | translation | machine translation | zero-shot machine translation | nan |
| natural language processing | text | classification | medical classification | multi-label classification of biomedical texts | convolutional nerual network with per-label attention |
| natural language processing | text | extraction | medical extraction | entity extraction using GAN | nrc-medner-eval |
| natural language processing | text | extraction | medical extraction | entity extraction using GAN | mimic_annotations |
| natural language processing | text | extraction | medical extraction | entity extraction using GAN | healthinf2020 |
| natural language processing | text | extraction | medical extraction | semantic similarity | biobert |
| natural language processing | text | extraction | medical extraction | semantic similarity | characterbert (base, medical, ensemble) |
| natural language processing | text | extraction | medical extraction | semantic similarity | macbert-large |
| natural language processing | text | extraction | medical extraction | semantic similarity | scibert uncased |
| natural language processing | text | extraction | medical extraction | semantic similarity | scibert cased |
| natural language processing | text | extraction | medical extraction | clinical concept extraction | bertlarge(mimic) |
| natural language processing | text | extraction | medical extraction | clinical concept extraction | characterbert(base, medical) |
| natural language processing | text | extraction | medical extraction | clinical concept extraction | clinicalbert |
| natural language processing | text | extraction | medical extraction | clinical concept extraction | elmo |
| natural language processing | text | extraction | medical extraction | clinical concept extraction | debruijn et al. |
| natural language processing | text | extraction | medical extraction | drug-drug interaction extraction | desc+mol+scibert |
| natural language processing | text | extraction | medical extraction | participant intervention comparison outcome extraction | pubmedbert uncased |
| natural language processing | text | extraction | medical extraction | participant intervention comparison outcome extraction | scibert |
| natural language processing | text | extraction | medical extraction | participant intervention comparison outcome extraction | bi-lstm |
| natural language processing | text | translation | medical translation | clinical language translation | unsupervised natural language representations |
| natural language processing | text | recognition | named entity recognition | multi-grained named entity recognition | nan |
| natural language processing | text | recognition | named entity recognition | named entity recognition | nan |
| natural language processing | text | recognition | named entity recognition | low resource named entity recognition | nan |
| natural language processing | text | recognition | named entity recognition | nested named entity recognition | nan |
| natural language processing | text | recognition | named entity recognition | cross-domain named entity recognition | nan |
| natural language processing | text | recognition | named entity recognition | multilingual named entity recognition | nan |
| natural language processing | text | recognition | named entity recognition | few-shot NER | nan |
| natural language processing | text | recognition | named entity recognition | multi-grained named entity recognition | nan |
| natural language processing | text | language-modelling | parsing | semantic parsing | nan |
| natural language processing | text | language-modelling | parsing | amr parsing | nan |
| natural language processing | text | language-modelling | parsing | semantic dependency parsing | nan |
| natural language processing | text | language-modelling | parsing | drs parsing | nan |
| natural language processing | text | language-modelling | parsing | ucca parsing | nan |
| natural language processing | text | language-modelling | parsing | dependency parsing | nan |
| natural language processing | text | language-modelling | parsing | transition-based dependency parsing | nan |
| natural language processing | text | language-modelling | parsing | cross-lingual zero-shot dependency parsing | nan |
| natural language processing | text | language-modelling | parsing | constituency parsing | nan |
| natural language processing | text | language-modelling | parsing | discourse parsing | nan |
| natural language processing | text | conversion | prediction | prosody prediction | nan |
| natural language processing | text | question answering | question answering | factual visual question answering | nan |
| natural language processing | text | question answering | question answering | knowledge based question answering | nan |
| natural language processing | text | reasoning | knowledge representation and reasoning | knowledge based question answering | nan |
| natural language processing | text | question answering | question answering | community question answering | nan |
| natural language processing | text | question answering | question answering | memex question answering | nan |
| natural language processing | text | question answering | question answering | embodied question answering | nan |
| natural language processing | text | reasoning | knowledge representation and reasoning | logical reasoning question answering | nan |
| natural language processing | text | question answering | question answering | cross-lingual question answering | nan |
| natural language processing | text | question answering | question answering | generative question answering | nan |
| natural language processing | text | question answering | question answering | open-domain question answering | nan |
| natural language processing | text | question answering | question answering | question answering | nan |
| natural language processing | text | question answering | question answering | answer selection | nan |
| natural language processing | text | question answering | question answering | question quality assessment | nan |
| natural language processing | text | question answering | question answering | mathematical question answering | nan |
| natural language processing | text | question answering | question answering | visual question answering | nan |
| natural language processing | text | question answering | question answering | machine reading comprehension | nan |
| natural language processing | text | question answering | question answering | multiple choice QA | nan |
| natural language processing | text | reasoning | knowledge representation and reasoning | natural language transduction | nan |
| natural language processing | text | language-modelling | segmentation | discourse segmentation | nan |
| natural language processing | text | language-modelling | sentence embedding | sentence embeddings for biomedical text | supervised combination of jaccard |
| natural language processing | text | language-modelling | sentence embedding | sentence embeddings for biomedical text | q-gram |
| natural language processing | text | language-modelling | sentence embedding | sentence embeddings for biomedical text | sent2vec |
| natural language processing | text | language-modelling | sentence embedding | sentence embeddings for biomedical text | paragraph vector dm |
| natural language processing | text | language-modelling | sentence embedding | sentence embeddings for biomedical text | skip-thoughts |
| natural language processing | text | language-modelling | sentence embedding | sentence embeddings for biomedical text | fasttext |
| natural language processing | text | language-modelling | sentence embedding | sentence embeddings for biomedical text | biosentvec |
| natural language processing | text | language-modelling | sentence embedding | sentence embeddings for biomedical text | paragraph vector |
| natural language processing | text | language-modelling | sentence embedding | joint multilingual sentence representation | nan |
| natural language processing | text | language-modelling | sentence embedding | sentence compression | nan |
| natural language processing | text | language-modelling | sentence embedding | sentence embeddings | nan |
| natural language processing | text | language-modelling | sentence/word embedding | multilingual NLP | nan |
| natural language processing | text | extraction | similiarity extraction | cross-lingual semantic textual similarity | nan |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | smart-roberta large |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | structbertroberta ensemble |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | mnet-sim |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | t5-11b |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | albert |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | xlnet |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | roberta |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | electra |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | efl |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | ernie 2.0 large |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | t5-3b |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | distilbert |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | mlm+ del-word |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | realformer |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | t5-large |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | spanbert |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | t5-base |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | ernie 2.0 base |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | t5-small |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | charformer-tall |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | ernie |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | 24hbert |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | tinybert |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | use_t |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | bigbird |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | simcse-robertalarge |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | trans-encoder-roberta-large-cross |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | trans-encoder-bert-large-bi |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | sroberta-nli-stsb-large |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | sbert-stsb-base |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | trans-encoder-roberta-base-cross |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | sbert-stsb-large |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | fnet-large |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | trans-encoder-bert-base-bi |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | pearl |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | sbert-nli-large |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | mirror-roberta-base |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | dino |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | sroberta-nli-base |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | sbert-nli-base |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | mirror-bert-base |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | bertlarge-flow |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | is-bert-nli |
| natural language processing | text | extraction | similiarity extraction | semantic textual similarity | deberta |
| natural language processing | text | extraction | similiarity extraction | semantic similarity | dependency tree-lstm |
| natural language processing | text | extraction | similiarity extraction | semantic similarity | combine-skip |
| natural language processing | text | extraction | similiarity extraction | semantic similarity | bidirectional lstm |
| natural language processing | text | extraction | similiarity extraction | semantic similarity | lstm |
| natural language processing | text | extraction | similiarity extraction | semantic similarity | doc2vecc |
| natural language processing | text | extraction | similiarity extraction | semantic similarity | ncbi_bert(base) (p+m) |
| natural language processing | text | extraction | similiarity extraction | semantic similarity | bert-base uncased |
| natural language processing | sound, audio | classification | sound classification | vowel classification | nan |
| natural language processing | sound, audio | classification | sound classification | bird classification | nan |
| natural language processing | sound, audio | classification | sound classification | self-supervised sound classification | nan |
| natural language processing | sound, audio | classification | sound classification | environmental sound classification | nan |
| natural language processing | sound, audio | classification | sound classification | acoustic scene classification | nan |
| natural language processing | sound, audio | classification | sound classification | audio classification | nan |
| natural language processing | sound, audio | detection | sound detection | bird audio detection | nan |
| natural language processing | sound, audio | detection | sound detection | sound event detection | nan |
| natural language processing | sound, audio | detection | sound detection | acoustic novelty detection | nan |
| natural language processing | sound, audio | detection | sound detection | sound event localization and detection | nan |
| natural language processing | sound, audio | natural language generation | sound generation | audio generation | nan |
| natural language processing | sound, audio | natural language generation | sound generation | music generation | nan |
| natural language processing | sound, audio | recognition | sound identification | language identification | nan |
| natural language processing | sound, audio | recognition | sound identification | language identification | nan |
| natural language processing | sound, audio | recognition | sound identification | dialect identification | nan |
| natural language processing | sound, audio | recognition | sound identification | native language identification | nan |
| natural language processing | sound, audio | recognition | sound recognition | video emotion recognition | nan |
| natural language processing | sound, audio | recognition | sound recognition | speaker recognition | nan |
| natural language processing | sound, audio | recognition | sound recognition | speaker recognition | nan |
| natural language processing | sound, audio | recognition | sound recognition | stext-independent speaker recognition | nan |
| natural language processing | sound, audio | recognition | sound separation | peaker separation | nan |
| natural language processing | sound, audio | recognition | sound separation | peaker separation | nan |
| natural language processing | sound, audio | recognition | sound separation | multi-speaker source separation | nan |
| natural language processing | sound, audio | detection | speech detection | synthetic speech detection | nan |
| natural language processing | sound, audio | detection | speech detection | counterspeech detection | nan |
| natural language processing | sound, audio | extraction | speech extraction | speech extraction | nan |
| natural language processing | sound, audio | natural language generation | speech generation | dialogue generation | nan |
| natural language processing | sound, audio | natural language generation | speech generation | audio super-resolution | nan |
| natural language processing | sound, audio | recognition | speech recognition | noisy speech recognition | nan |
| natural language processing | sound, audio | recognition | speech recognition | accented speech recognition | nan |
| natural language processing | sound, audio | recognition | speech recognition | sequence-to-sequence speech recognition | nan |
| natural language processing | sound, audio | recognition | speech recognition | robust speech recognition | nan |
| natural language processing | sound, audio | recognition | speech recognition | distant speech recognition | nan |
| natural language processing | sound, audio | recognition | speech recognition | voice query recognition | nan |
| natural language processing | sound, audio | recognition | speech recognition | unsupervised speech recognition | nan |
| natural language processing | sound, audio | recognition | speech recognition | audio-visual speech recognition | nan |
| natural language processing | sound, audio | recognition | speech recognition | automatic speech recognition | nan |
| natural language processing | sound, audio | recognition | speech recognition | speech recognition | nan |
| natural language processing | sound, audio | recognition | speech recognition | visual speech recognition | nan |
| natural language processing | sound, audio | recognition | speech recognition | geometric-deep-learning-on-graphs-and | monet |
| natural language processing | sound, audio | recognition | speech recognition | using-filter-banks-in-convolutional-neural | convolution |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | dcnn |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | dense-connections |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | alexnet |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | k-means-clustering |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | vgg-16 |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | softmax |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | local-response-normalization |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | convolution |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | max-pooling |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | 1x1-convolution |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | relu |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | dropout |
| natural language processing | sound, audio | recognition | speech recognition | intra-layer-nonuniform-quantization-for-deep | grouped-convolution |
| natural language processing | sound, audio | recognition | speech recognition | squantizer-simultaneous-learning-for-both | tanh-activation |
| natural language processing | sound, audio | recognition | speech recognition | squantizer-simultaneous-learning-for-both | softmax |
| natural language processing | sound, audio | recognition | speech recognition | squantizer-simultaneous-learning-for-both | lstm |
| natural language processing | sound, audio | recognition | speech recognition | squantizer-simultaneous-learning-for-both | sigmoid-activation |
| natural language processing | sound, audio | recognition | speech recognition | a-survey-of-the-recent-architectures-of-deep | tanh-activation |
| natural language processing | sound, audio | recognition | speech recognition | a-survey-of-the-recent-architectures-of-deep | mish |
| natural language processing | sound, audio | recognition | speech recognition | a-survey-of-the-recent-architectures-of-deep | softplus |
| natural language processing | sound, audio | conversion | speech-image conversion | speech-to-gesture translation | nan |
| natural language processing | sound, audio | natural language generation | speech-speech conversion | speech-to-speech translation | nan |
| natural language processing | sound, audio | natural language generation | speech-text conversion | speech-to-text translation | nan |
| natural language processing | sound, audio | natural language generation | speech-text conversion | simultaneous speech-to-text translation | nan |
| natural language processing | text | natural language generation | summarization | extractive summarization | hahsum |
| natural language processing | text | natural language generation | summarization | extractive summarization | longformer-base |
| natural language processing | text | natural language generation | summarization | extractive summarization | abs |
| natural language processing | text | extraction | tagging | morphological tagging | mtg |
| natural language processing | text | extraction | tagging | morphological tagging | meta_tagger |
| natural language processing | text | extraction | tagging | morphological tagging | nmt-repr-analysis |
| natural language processing | text | extraction | tagging | morphological tagging | sclem2017-tagger |
| natural language processing | text | extraction | tagging | morphological tagging | contextualdecomposition-nlp |
| natural language processing | text | extraction | tagging | morphological tagging | ebm-sanskrit-word-segmentation |
| natural language processing | text | extraction | tagging | morphological tagging | ku-dependency-parser2 |
| natural language processing | text | extraction | tagging | morphological tagging | seq-morph-tagger |
| natural language processing | text | extraction | tagging | morphological tagging | morpheus |
| natural language processing | text | extraction | tagging | morphological tagging | word-embeddings-eval-hy |
| natural language processing | text | extraction | tagging | morphological tagging | morph_analyzer |
| natural language processing | text | extraction | tagging | morphological tagging | inforex |
| natural language processing | text | extraction | tagging | morphological tagging | sanskrit-morphological-taggers |
| natural language processing | text | extraction | tagging | morphological tagging | trankit |
| natural language processing | text | extraction | tagging | morphological tagging | alephbert |
| natural language processing | text | extraction | tagging | temporal tagging | b2b |
| natural language processing | text | extraction | tagging | temporal tagging | r2r |
| natural language processing | text | extraction | tagging | temporal tagging | datebert |
| natural language processing | text | extraction | tagging | temporal tagging | bert-base |
| natural language processing | text | extraction | tagging | unsupervised part-of-speech tagging | anchor |
| natural language processing | text | extraction | tagging | part-of-speech tagging | meta bilstm |
| natural language processing | text | classification | text classification | text classification | xlnet |
| natural language processing | text | classification | text classification | text classification | use_t+cnn |
| natural language processing | text | classification | text classification | text classification | ernie-doc-large |
| natural language processing | text | classification | text classification | text classification | ssgc |
| natural language processing | text | classification | text classification | text classification | orthogonalized soft vsm |
| natural language processing | text | classification | text classification | text classification | robertagcn |
| natural language processing | text | classification | text classification | text classification | bert-itpt-fit |
| natural language processing | text | classification | text classification | text classification | 1-6 bertgcn |
| natural language processing | text | classification | text classification | text classification | hahnn (cnn) |
| natural language processing | text | classification | text classification | multi-label text classification | tagbert |
| natural language processing | text | classification | text classification | multi-label text classification | lsan |
| natural language processing | text | classification | text classification | multi-label text classification | cb-ntr |
| natural language processing | text | classification | text classification | multi-label text classification | bert-base |
| natural language processing | text | classification | text classification | multi-label text classification | xgboost |
| natural language processing | text | classification | text classification | multi-label text classification | hlan |
| natural language processing | text | classification | text classification | multi-label text classification | laha |
| natural language processing | text | classification | text classification | multi-label text classification | d2sbert using sequence attention |
| natural language processing | text | classification | text classification | text categorization | nan |
| natural language processing | text | classification | text classification | semi-supervised text classification | mixtext |
| natural language processing | text | classification | text classification | semi-supervised text classification | vampire |
| natural language processing | text | classification | text classification | semi-supervised text classification | aaai_clf |
| natural language processing | text | classification | text classification | semi-supervised text classification | flitext |
| natural language processing | text | classification | text classification | semi-supervised text classification | flowgmm |
| natural language processing | text | classification | text classification | semi-supervised text classification | deconv_paragraph_representation |
| natural language processing | text | classification | text classification | cross-domain text classification | nan |
| natural language processing | text | classification | text classification | hierarchical text classification | rmdl |
| natural language processing | text | classification | text classification | hierarchical text classification | hdltex |
| natural language processing | text | classification | text classification | hierarchical text classification | cophe |
| natural language processing | text | classification | text classification | hierarchical text classification | swin transformer |
| natural language processing | text | classification | text classification | hierarchical text classification | hypertext |
| natural language processing | text | classification | text classification | hierarchical text classification | autohensgnn |
| natural language processing | text | classification | text classification | hierarchical text classification | zoo |
| natural language processing | text | classification | text classification | text clustering | g-bat |
| natural language processing | text | classification | text classification | short text clustering | sccl |
| natural language processing | text | classification | text classification | short text clustering | deep ecic |
| natural language processing | text | classification | text classification | few-shot text classification | induction networks |
| natural language processing | text | classification | text classification | toxic comment classification | gbert/gelectra ensemble |
| natural language processing | text | classification | text classification | meme classification | hatedetectron27 |
| natural language processing | text | classification | text classification | news classification | xlmindic-base-uniscript |
| natural language processing | text | classification | text classification | news classification | multimodal(vit+bert, input: image + body) |
| natural language processing | text | classification | text classification | news classification | indicbert base |
| natural language processing | text | classification | text classification | news classification | xlmindic-base-multiscript |
| natural language processing | text | classification | text classification | poem meters classification | bilstm |
| natural language processing | text | classification | text classification | dialog act classification | utt-att-birnn |
| natural language processing | text | detection | text detection | rumor detection | parsbert+pcapsnet +sa+title+ auxiliary |
| natural language processing | text | detection | text detection | open intent detection | bi-model with decoder |
| natural language processing | text | detection | text detection | grammatical error detection | vernet |
| natural language processing | text | detection | text detection | grammatical error detection | bilstm-joint |
| natural language processing | text | detection | text detection | grammatical error detection | ann+pat+mt |
| natural language processing | text | detection | text detection | grammatical error detection | bi-lstm + lmcost |
| natural language processing | text | detection | text detection | grammatical error detection | bi-lstm + err pos gr |
| natural language processing | text | detection | text detection | grammatical error detection | bi-lstm+ error- and grammaticality-specific word embeddings |
| natural language processing | text | detection | text detection | grammatical error detection | bi-lstm + charattn |
| natural language processing | text | detection | text detection | grammatical error detection | bi-lstm |
| natural language processing | text | detection | text detection | fake news detection | neural method from mohtarami et al. + tf-idf |
| natural language processing | text | detection | text detection | fake news detection | neural method from mohtarami et al. |
| natural language processing | text | detection | text detection | fake news detection | baseline based on skip-thought embeddings |
| natural language processing | text | detection | text detection | fake news detection | baseline based on word2vec + hand-crafted features |
| natural language processing | text | detection | text detection | fake news detection | neural baseline based on bi-directional lstms |
| natural language processing | text | detection | text detection | fake news detection | text-transformers + five-fold five model cross-validation +pseudo label algorithm |
| natural language processing | text | detection | text detection | fake news detection | grover-mega |
| natural language processing | text | detection | text detection | fake news detection | seplveda-torres r., vicente m., saquete e., lloret e., palomar m. (2021) |
| natural language processing | text | detection | text detection | fake news detection | bhatt et al. |
| natural language processing | text | detection | text detection | fake news detection | bi-lstm |
| natural language processing | text | detection | text detection | fake news detection | 3rd place at fnc-1 - team ucl machine reading |
| natural language processing | text | detection | text detection | fake news detection | bert-large |
| natural language processing | text | detection | text detection | fake news detection | gpt-2 |
| natural language processing | text | detection | text detection | fake news detection | hybrid cnns |
| natural language processing | text | detection | text detection | fake news detection | cnns |
| natural language processing | text | detection | text detection | fake news detection | bi-lstms |
| natural language processing | text | detection | text detection | fake news detection | auxiliary indicbert |
| natural language processing | text | detection | text detection | fake news detection | ensemble model + heuristic post-processing |
| natural language processing | text | detection | text detection | fake news detection | textrnn |
| natural language processing | text | detection | text detection | intent detection | bi-model with decoder |
| natural language processing | text | detection | text detection | intent detection | transformer-capsule |
| natural language processing | text | detection | text detection | intent detection | attention encoder-decoder nn |
| natural language processing | text | detection | text detection | intent detection | joint model with recurrent slot label context |
| natural language processing | text | detection | text detection | intent detection | sf-id (blstm) |
| natural language processing | text | detection | text detection | intent detection | stack-propagation (+bert) |
| natural language processing | text | detection | text detection | intent detection | delta (blstm-crf) |
| natural language processing | text | detection | text detection | intent detection | capsule-nlu |
| natural language processing | text | detection | text detection | intent detection | slot-gated blstm with attension |
| natural language processing | text | detection | text detection | intent detection | joint bert + crf |
| natural language processing | text | detection | text detection | intent detection | joint bert |
| natural language processing | text | detection | text detection | intent detection | context encoder |
| natural language processing | text | detection | text detection | intent detection | plain-lstm |
| natural language processing | text | detection | text detection | intent detection | linear-ngrams |
| natural language processing | text | detection | text detection | intent detection | glove-lstm |
| natural language processing | text | detection | text detection | intent detection | gl-gin |
| natural language processing | text | detection | text detection | connective detection | nan |
| natural language processing | text | detection | text detection | abuse detection | nan |
| natural language processing | text | detection | text detection | bias detection | nan |
| natural language processing | text | detection | text detection | negation scope resolution | nan |
| natural language processing | text | detection | text detection | negation detection | nan |
| natural language processing | text | detection | text detection | satire detection | nan |
| natural language processing | text | detection | text detection | humor detection | nan |
| natural language processing | text | detection | text detection | gender bias detection | nan |
| natural language processing | text | detection | text detection | incongruity detection | nan |
| natural language processing | text | detection | text detection | stance detection | nan |
| natural language processing | text | detection | text detection | propaganda detection | nan |
| natural language processing | text | detection | text detection | speculation detection | nan |
| natural language processing | text | detection | text detection | zero-shot out-of-domain detection | nan |
| natural language processing | sound, audio | natural language generation | text generation | dialogue state tracking | nan |
| natural language processing | sound, audio | natural language generation | text generation | task-oriented dialogue systems | nan |
| natural language processing | text | natural language generation | text generation | story generation | nan |
| natural language processing | text | natural language generation | text generation | question-answer generation | nan |
| natural language processing | text | natural language generation | text generation | data-to-text generation | nan |
| natural language processing | text | natural language generation | text generation | paraphrase generation | nan |
| natural language processing | text | natural language generation | text generation | dialogue generation | nan |
| natural language processing | text | natural language generation | text generation | question generation | nan |
| natural language processing | text | natural language generation | text generation | table-to-text generation | nan |
| natural language processing | text | natural language generation | text generation | visual storytelling | nan |
| natural language processing | text | natural language generation | text generation | distractor generation | nan |
| natural language processing | text | natural language generation | text generation | spelling correction | nan |
| natural language processing | text | natural language generation | text generation | text style transfer | nan |
| natural language processing | text | natural language generation | text generation | news generation | nan |
| natural language processing | text | natural language generation | text generation | story completion | nan |
| natural language processing | text | natural language generation | text generation | concept-to-text generation | nan |
| natural language processing | text | natural language generation | text generation | chatbot | nan |
| natural language processing | text | natural language generation | text generation | fact-based text editing | nan |
| natural language processing | text | natural language generation | text generation | blackout poetry generation | nan |
| natural language processing | text | natural language generation | text generation | text simplification | nan |
| natural language processing | text | natural language generation | text generation | sonnet generation | nan |
| natural language processing | text | natural language generation | text generation | paper generation | nan |
| natural language processing | text | natural language generation | text generation | text infilling | nan |
| natural language processing | text | natural language generation | text generation | conditional text generation | nan |
| natural language processing | text | natural language generation | text generation | text generation | nan |
| natural language processing | sound, audio | natural language generation | text generation | goal-oriented dialog | nan |
| natural language processing | text | natural language generation | text summarization | extractive text summarization | nan |
| natural language processing | text | natural language generation | text summarization | abstractive text summarization | nan |
| natural language processing | text | natural language generation | text summarization | text summarization | nan |
| natural language processing | text | conversion | text-image conversion | zero-shot text-to-image generation | nan |
| natural language processing | sound, audio | natural language generation | text-sound conversion | text-to-speech synthesis | nan |
| natural language processing | text | natural language generation | text-speech conversion | text-to-speech synthesis | nan |
| natural language processing | text | natural language generation | text-speech conversion | zero-shot multi-speaker tts | nan |
| natural language processing | text | natural language generation | text-text conversion | short-text conversation | nan |
| natural language processing | text | conversion | text-video conversion | text-to-video search | nan |
| natural language processing | text | classification | topic classification | topic models | bayesian smm |
| natural language processing | text | classification | topic classification | topic models | josh |
| natural language processing | text | classification | topic classification | topic models | josh |
| natural language processing | text | classification | topic classification | topic coverage | nan |
| natural language processing | text | language-modelling | vector embedding | phrase vector embedding | nan |
| natural language processing | text | natural language generation | video-text conversion | visual storytelling | nan |
| natural language processing | sound, audio | natural language generation | voice conversion | zero-shot multi-speaker tts | nan |
| natural language processing | sound, audio | natural language generation | voice conversion | voice conversion | nan |
| natural language processing | text | language-modelling | word embedding | multi-word expression embedding | nan |
| natural language processing | text | language-modelling | word embedding | multilingual word embedding | nan |
| natural language processing | text | language-modelling | word embedding | learning word embeddings | nan |
| natural language processing | text | language-modelling | word embedding | word embedding | nan |
| natural language processing | text | language-modelling | word embedding | conceptualized word representation | nan |
| natural language processing | text | language-modelling | word embedding | diachronic word embeddings | nan |
| robotics | multiple | 3d | reconstruction | 3D reconstruction, 3d face reconstruction | deca |
| robotics | multiple | 3d | reconstruction | 3D reconstruction, 3d face reconstruction | 3ddfa_v2 |
| robotics | multiple | 3d | reconstruction | 3D reconstruction, 3d face reconstruction | sadrnet |
| robotics | multiple | 3d | reconstruction | 3D reconstruction, 3d face reconstruction | rrf |
| robotics | multiple | 3d | reconstruction | 3D reconstruction, 3d face reconstruction | arch |
| robotics | multiple | 3d | reconstruction | 3D reconstruction, 3d face reconstruction | codeslam |
| robotics | multiple | 3d | reconstruction | 3D reconstruction, 3d face reconstruction | neuralrecon |
| robotics | multiple | 3d | verification | face verification | vargfacenet |
| robotics | multiple | 3d | verification | face verification | dual-agent gans |
| robotics | multiple | 3d | verification | face verification | seqface, 1 resnet-64 |
| robotics | multiple | 3d | verification | face verification | prodpoly |
| robotics | multiple | 3d | verification | face verification | headsharing: sh-kd |
| robotics | multiple | 3d | verification | face verification | sv-am-softmax |
| robotics | multiple | 3d | verification | face verification | discface |
| robotics | multiple | 3d | verification | face verification | fpn |
| robotics | multiple | 3d | verification | face verification | lightcnn-29+dvg |
| robotics | multiple | 3d | animation | 3d face animation | v |
| robotics | multiple | 3d | generation | 3d shape generation | nan |
| robotics | multiple | 3d | render | neural rendering | non-convolutional deep network |
| robotics | multiple | 3d | estimation | 3d pose estimation, 3d absolute human pose estimation | nan |
| robotics | multiple | control | control | continuous control | smuzero |
| robotics | multiple | control | control | continuous control | sac gsde |
| robotics | multiple | control | control | continuous control | drq |
| robotics | multiple | control | control | continuous control | sac |
| robotics | multiple | control | control | drone controller | nan |
| robotics | multiple | control | control | steering control | fm-net |
| robotics | multiple | control | control | car racing | generative neural network models, reinforcement learning |
| robotics | multiple | motion-planning | planning | motion planning, optimal motion planning | complex-yolo |
| robotics | multiple | motion-planning | planning | robot task planning | reinforcement learning |
| robotics | multiple | reinforcement learning | reinforcement learning | offline reinforcement learning | reinforcement learning |
| robotics | multiple | reinforcement learning | reinforcement learning | safe exploration | reinforcement learning |
| robotics | multiple | reinforcement learning | reinforcement learning | temporal logic | reinforcement learning |
| robotics | multiple | reinforcement learning | reinforcement learning | model-based reinforcement learning | reinforcement learning |
| robotics | multiple | navigation | navigation | robot navigation, marine robot navigation | thda |
| robotics | multiple | navigation | navigation | robot navigation, marine robot navigation | vo |
| robotics | multiple | navigation | navigation | robot navigation, marine robot navigation | semexp |
| robotics | multiple | navigation | navigation | vision and language navigation | human |
| robotics | multiple | navigation | navigation | vision and language navigation | arc+l2stop |
| robotics | multiple | navigation | navigation | vision and language navigation | hierarchical cross-modal agent |
| robotics | multiple | navigation | navigation | pointgoal navigation | depth ddppo |
| robotics | multiple | navigation | recognition | sequential place recognition | rnn+cnn |
| robotics | multiple | navigation | recognition | sequential place recognition | deepseqslam |
| robotics | multiple | navigation | navigation | visual navigation | babywalk |
| robotics | multiple | navigation | navigation | visual navigation | prevalent |
| robotics | multiple | navigation | navigation | visual navigation | mvv-in |
| robotics | multiple | navigation | navigation | visual navigation | popart-impala |
| robotics | multiple | navigation | navigation | visual navigation | prevalent |
| robotics | multiple | navigation | navigation | autonomous flight | nan |
| robotics | multiple | navigation | learning | sequential place learning | deepseqslam |
| robotics | multiple | navigation | learning | sequential place learning | rnn+cnn |
| robotics | multiple | navigation | navigation | vnla | vnla |
| robotics | multiple | detection | detection | touch detection | pytouch |
| robotics | multiple | detection | detection | radar object detection | raddet |
| robotics | multiple | detection | detection | radar object detection | rodnet |
| robotics | multiple | other robots | other robots | industrial robots, trajectory planning | nan |
| robotics | multiple | other robots | other robots | legged robot | nan |
| robotics | multiple | motion-planning | planning | complex-yolo-real-time-3d-object-detection-on | yolov2 |
| robotics | multiple | motion-planning | planning | complex-yolo-real-time-3d-object-detection-on | average-pooling |
| robotics | multiple | motion-planning | planning | complex-yolo-real-time-3d-object-detection-on | global-average-pooling |
| robotics | multiple | motion-planning | planning | complex-yolo-real-time-3d-object-detection-on | convolution |
| robotics | multiple | motion-planning | planning | complex-yolo-real-time-3d-object-detection-on | softmax |
| robotics | multiple | motion-planning | planning | complex-yolo-real-time-3d-object-detection-on | max-pooling |
| robotics | multiple | motion-planning | planning | complex-yolo-real-time-3d-object-detection-on | darknet-19 |
| robotics | multiple | motion-planning | planning | complex-yolo-real-time-3d-object-detection-on | 1x1-convolution |
| robotics | multiple | motion-planning | planning | complex-yolo-real-time-3d-object-detection-on | batch-normalization |