{"url":"/task/action-recognition-in-videos-2","name":"Action Recognition In Videos","slug":"action-recognition-in-videos-2","description_markdown":"**Action Recognition in Videos** is a task in computer vision and pattern recognition where the goal is to identify and categorize human actions performed in a video sequence. The task involves analyzing the spatiotemporal dynamics of the actions and mapping them to a predefined set of action classes, such as running, jumping, or swimming.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":124,"papers_with_code":71,"benchmarks":17,"benchmark_tables_in_archive":17,"benchmark_tables_shown":17,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":17,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/action-recognition-in-videos-on-jester-1","slug":"action-recognition-in-videos-on-jester-1","dataset":"Jester (Gesture Recognition)","dataset_url":"/dataset/jester-gesture-recognition","rows_in_archive":9,"metrics":["Val"],"first_row_in_archive_order":{"model":"CPNet Res34, 5 CP","paper_title":"Learning Video Representations from Correspondence Proposals","paper_url":"/paper/learning-video-representations-from","paper_date":"2019-05-20","arxiv_id":"1905.07853","code_links":[{"title":"xingyul/meteornet","url":"https://github.com/xingyul/meteornet"},{"title":"xingyul/cpnet","url":"https://github.com/xingyul/cpnet"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-pku-mmd","slug":"action-recognition-in-videos-on-pku-mmd","dataset":"PKU-MMD","dataset_url":"/dataset/pku-mmd","rows_in_archive":5,"metrics":["X-Sub","X-View"],"first_row_in_archive_order":{"model":"DSCNet (RGB + Pose)","paper_title":"A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities","paper_url":"/paper/a-dense-sparse-complementary-network-for","paper_date":"2023-12-28","arxiv_id":null,"code_links":[{"title":"Maxchengqin/DSCNet","url":"https://github.com/Maxchengqin/DSCNet"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-ucf101-2","slug":"action-recognition-in-videos-on-ucf101-2","dataset":"UCF101","dataset_url":"/dataset/ucf101","rows_in_archive":5,"metrics":["3-fold Accuracy"],"first_row_in_archive_order":{"model":"STM (ImageNet+Kinetics pretrain)","paper_title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","paper_url":"/paper/stm-spatiotemporal-and-motion-encoding-for","paper_date":"2019-08-07","arxiv_id":"1908.02486","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-something-3","slug":"action-recognition-in-videos-on-something-3","dataset":"Something-Something V2","dataset_url":"/dataset/something-something-v2","rows_in_archive":4,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"STM (16 frames, ImageNet pretraining)","paper_title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","paper_url":"/paper/stm-spatiotemporal-and-motion-encoding-for","paper_date":"2019-08-07","arxiv_id":"1908.02486","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-kinetics-400-1","slug":"action-recognition-in-videos-on-kinetics-400-1","dataset":"Kinetics-400","dataset_url":"/dataset/kinetics","rows_in_archive":3,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"Florence","paper_title":"Florence: A New Foundation Model for Computer Vision","paper_url":"/paper/florence-a-new-foundation-model-for-computer","paper_date":"2021-11-22","arxiv_id":"2111.11432","code_links":[{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/florence2"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-something-2","slug":"action-recognition-in-videos-on-something-2","dataset":"Something-Something V1","dataset_url":"/dataset/something-something-v1","rows_in_archive":3,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"STM (16 frames, ImageNet pretraining)","paper_title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","paper_url":"/paper/stm-spatiotemporal-and-motion-encoding-for","paper_date":"2019-08-07","arxiv_id":"1908.02486","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-ava-v2-2","slug":"action-recognition-in-videos-on-ava-v2-2","dataset":"AVA v2.2","dataset_url":"/dataset/ava","rows_in_archive":2,"metrics":["mAP (Val)"],"first_row_in_archive_order":{"model":"YOWO+LFB*","paper_title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","paper_url":"/paper/you-only-watch-once-a-unified-cnn","paper_date":"2019-11-15","arxiv_id":"1911.06644","code_links":[{"title":"wei-tim/YOWO","url":"https://github.com/wei-tim/YOWO"},{"title":"zwtu/YOWO-Paddle","url":"https://github.com/zwtu/YOWO-Paddle"},{"title":"BoChenUIUC/YOWO","url":"https://github.com/BoChenUIUC/YOWO"},{"title":"nuschandra/Tennis-Stroke-Detection","url":"https://github.com/nuschandra/Tennis-Stroke-Detection"},{"title":"Stepphonwol/my_yowo","url":"https://github.com/Stepphonwol/my_yowo"}],"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":2}}},{"leaderboard":"/sota/action-recognition-in-videos-on-fs-something","slug":"action-recognition-in-videos-on-fs-something","dataset":"FS-Something-Something V2-Small","dataset_url":null,"rows_in_archive":2,"metrics":["Top-1 Accuracy(5-Way-1-Shot)","Top-1 Accuracy(5-Way-5-Shot)"],"first_row_in_archive_order":{"model":"ITANet","paper_title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","paper_url":"/paper/learning-implicit-temporal-alignment-for-few","paper_date":"2021-05-11","arxiv_id":"2105.04823","code_links":[{"title":"tonysy/PyAction","url":"https://github.com/tonysy/PyAction"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-fs-something-1","slug":"action-recognition-in-videos-on-fs-something-1","dataset":"FS-Something-Something V2-Full","dataset_url":null,"rows_in_archive":2,"metrics":["Top-1 Accuracy(5-Way-1-Shot)","Top-1 Accuracy(5-Way-5-Shot)"],"first_row_in_archive_order":{"model":"ITANet","paper_title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","paper_url":"/paper/learning-implicit-temporal-alignment-for-few","paper_date":"2021-05-11","arxiv_id":"2105.04823","code_links":[{"title":"tonysy/PyAction","url":"https://github.com/tonysy/PyAction"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-sports-1m-1","slug":"action-recognition-in-videos-on-sports-1m-1","dataset":"Sports-1M","dataset_url":"/dataset/sports-1m","rows_in_archive":2,"metrics":["Video hit@1","Video hit@5"],"first_row_in_archive_order":{"model":"G-Blend","paper_title":"What Makes Training Multi-Modal Classification Networks Hard?","paper_url":"/paper/what-makes-training-multi-modal-networks-hard","paper_date":"2019-05-29","arxiv_id":"1905.12681","code_links":[{"title":"facebookresearch/R2Plus1D","url":"https://github.com/facebookresearch/R2Plus1D"},{"title":"facebookresearch/VMZ","url":"https://github.com/facebookresearch/VMZ"},{"title":"guide2157/ChulaXrayClassifier","url":"https://github.com/guide2157/ChulaXrayClassifier"}],"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/action-recognition-in-videos-on-thumos14-1","slug":"action-recognition-in-videos-on-thumos14-1","dataset":"THUMOS’14","dataset_url":"/dataset/thumos14-1","rows_in_archive":2,"metrics":["mAP@0.1","mAP@0.2","mAP@0.3","mAP@0.4","mAP@0.5"],"first_row_in_archive_order":{"model":"Single-stream R-C3D (two-way buffer)","paper_title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","paper_url":"/paper/r-c3d-region-convolutional-3d-network-for","paper_date":"2017-03-22","arxiv_id":"1703.07814","code_links":[{"title":"VisionLearningGroup/R-C3D","url":"https://github.com/VisionLearningGroup/R-C3D"},{"title":"2023-MindSpore-4/Code8","url":"https://github.com/2023-MindSpore-4/Code8/tree/main/C3D"},{"title":"MindSpore-paper-code-3/code6","url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/C3D"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/action-recognition-in-videos-on-activitynet-1","slug":"action-recognition-in-videos-on-activitynet-1","dataset":"ActivityNet","dataset_url":"/dataset/activitynet","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"LSTM + Pretrained on YT-8M","paper_title":"YouTube-8M: A Large-Scale Video Classification Benchmark","paper_url":"/paper/youtube-8m-a-large-scale-video-classification","paper_date":"2016-09-27","arxiv_id":"1609.08675","code_links":[{"title":"google/youtube-8m","url":"https://github.com/google/youtube-8m"},{"title":"AKASH2907/Content-based-Video-Recommendation","url":"https://github.com/AKASH2907/Content-based-Video-Recommendation"},{"title":"AKASH2907/Content-based-Video-Relevance-Prediction","url":"https://github.com/AKASH2907/Content-based-Video-Relevance-Prediction"},{"title":"taufikxu/youtube","url":"https://github.com/taufikxu/youtube"},{"title":"Cloud-Computing-IoT/speakEasy","url":"https://github.com/Cloud-Computing-IoT/speakEasy"},{"title":"Cloud-Computing-IoT/Cloud-Enabled-Smart-Speaker","url":"https://github.com/Cloud-Computing-IoT/Cloud-Enabled-Smart-Speaker"},{"title":"boseaslcohort/youtube-8m","url":"https://github.com/boseaslcohort/youtube-8m"}],"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}}},{"leaderboard":"/sota/action-recognition-in-videos-on-ava-v2-1","slug":"action-recognition-in-videos-on-ava-v2-1","dataset":"AVA v2.1","dataset_url":"/dataset/ava","rows_in_archive":1,"metrics":["mAP (Val)"],"first_row_in_archive_order":{"model":"YOWO+LFB*","paper_title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","paper_url":"/paper/you-only-watch-once-a-unified-cnn","paper_date":"2019-11-15","arxiv_id":"1911.06644","code_links":[{"title":"wei-tim/YOWO","url":"https://github.com/wei-tim/YOWO"},{"title":"zwtu/YOWO-Paddle","url":"https://github.com/zwtu/YOWO-Paddle"},{"title":"BoChenUIUC/YOWO","url":"https://github.com/BoChenUIUC/YOWO"},{"title":"nuschandra/Tennis-Stroke-Detection","url":"https://github.com/nuschandra/Tennis-Stroke-Detection"},{"title":"Stepphonwol/my_yowo","url":"https://github.com/Stepphonwol/my_yowo"}],"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":2}}},{"leaderboard":"/sota/action-recognition-in-videos-on-hmdb-51-1","slug":"action-recognition-in-videos-on-hmdb-51-1","dataset":"HMDB-51","dataset_url":"/dataset/hmdb51","rows_in_archive":1,"metrics":["Average accuracy of 3 splits"],"first_row_in_archive_order":{"model":"STM (ImageNet+Kinetics pretrain)","paper_title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","paper_url":"/paper/stm-spatiotemporal-and-motion-encoding-for","paper_date":"2019-08-07","arxiv_id":"1908.02486","code_links":[],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-kinetics-600","slug":"action-recognition-in-videos-on-kinetics-600","dataset":"Kinetics-600","dataset_url":"/dataset/kinetics-600","rows_in_archive":1,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"Florence","paper_title":"Florence: A New Foundation Model for Computer Vision","paper_url":"/paper/florence-a-new-foundation-model-for-computer","paper_date":"2021-11-22","arxiv_id":"2111.11432","code_links":[{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/florence2"}],"syntology":null}},{"leaderboard":"/sota/action-recognition-in-videos-on-minisports-1","slug":"action-recognition-in-videos-on-minisports-1","dataset":"miniSports","dataset_url":null,"rows_in_archive":1,"metrics":["Clip Hit@1","Video hit@1","Video hit@5"],"first_row_in_archive_order":{"model":"G-Blend","paper_title":"What Makes Training Multi-Modal Classification Networks Hard?","paper_url":"/paper/what-makes-training-multi-modal-networks-hard","paper_date":"2019-05-29","arxiv_id":"1905.12681","code_links":[{"title":"facebookresearch/R2Plus1D","url":"https://github.com/facebookresearch/R2Plus1D"},{"title":"facebookresearch/VMZ","url":"https://github.com/facebookresearch/VMZ"},{"title":"guide2157/ChulaXrayClassifier","url":"https://github.com/guide2157/ChulaXrayClassifier"}],"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/action-recognition-in-videos-on-ntu-rgb-d","slug":"action-recognition-in-videos-on-ntu-rgb-d","dataset":"NTU RGB+D","dataset_url":"/dataset/ntu-rgb-d","rows_in_archive":1,"metrics":["Accuracy (CS)"],"first_row_in_archive_order":{"model":"2D-3D-Softargmax (RGB only)","paper_title":"2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning","paper_url":"/paper/2d3d-pose-estimation-and-action-recognition","paper_date":"2018-02-26","arxiv_id":"1802.09232","code_links":[{"title":"dluvizon/deephar","url":"https://github.com/dluvizon/deephar"},{"title":"pminhtam/2D-3D_Multitask_Deep_Learning","url":"https://github.com/pminhtam/2D-3D_Multitask_Deep_Learning"}],"syntology":{"n":25,"n_ran":0,"n_unverified":25,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/ucf101","name":"UCF101","full_name":"UCF101 Human Actions dataset","num_papers_in_archive":1863},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/hmdb51","name":"HMDB51","full_name":"","num_papers_in_archive":839},{"url":"/dataset/activitynet","name":"ActivityNet","full_name":"","num_papers_in_archive":807},{"url":"/dataset/kinetics-400-1","name":"Kinetics 400","full_name":"","num_papers_in_archive":712},{"url":"/dataset/ntu-rgb-d","name":"NTU RGB+D","full_name":"","num_papers_in_archive":476},{"url":"/dataset/thumos14-1","name":"THUMOS14","full_name":"","num_papers_in_archive":318},{"url":"/dataset/something-something-v2","name":"Something-Something V2","full_name":"","num_papers_in_archive":290},{"url":"/dataset/sports-1m","name":"Sports-1M","full_name":"","num_papers_in_archive":164},{"url":"/dataset/kinetics-600","name":"Kinetics-600","full_name":"","num_papers_in_archive":148},{"url":"/dataset/something-something-v1","name":"Something-Something V1","full_name":"","num_papers_in_archive":117},{"url":"/dataset/ava","name":"AVA","full_name":"Atomic Visual Actions","num_papers_in_archive":113},{"url":"/dataset/pku-mmd","name":"PKU-MMD","full_name":"PKU-MMD","num_papers_in_archive":72},{"url":"/dataset/mtl-aqa","name":"MTL-AQA","full_name":"","num_papers_in_archive":33},{"url":"/dataset/jester-gesture-recognition","name":"Jester (Gesture Recognition)","full_name":"","num_papers_in_archive":16},{"url":"/dataset/cvb-a-video-dataset-of-cattle-visual","name":"CVB","full_name":"Video Dataset of Cattle Visual Behaviors","num_papers_in_archive":2},{"url":"/dataset/win-fail-action-understanding","name":"Win-Fail Action Understanding","full_name":"Win-Fail Action Understanding","num_papers_in_archive":1}],"subtasks":[{"url":"/task/action-anticipation","name":"Action Anticipation"}],"parent_tasks":[{"url":"/task/action-recognition-in-videos","name":"Action Recognition"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":71,"tagged_in_all":124,"items":[{"url":"/paper/learning-spatiotemporal-features-with-3d","title":"Learning Spatiotemporal Features with 3D Convolutional Networks","date":"2014-12-02","arxiv_id":"1412.0767","repositories_listed":29,"syntology":null},{"url":"/paper/temporal-segment-networks-towards-good","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","date":"2016-08-02","arxiv_id":"1608.00859","repositories_listed":22,"syntology":{"n":24,"n_ran":2,"n_unverified":22,"n_pointer_only":3}},{"url":"/paper/slowfast-networks-for-video-recognition","title":"SlowFast Networks for Video Recognition","date":"2018-12-10","arxiv_id":"1812.03982","repositories_listed":15,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/temporal-segment-networks-for-action","title":"Temporal Segment Networks for Action Recognition in Videos","date":"2017-05-08","arxiv_id":"1705.02953","repositories_listed":11,"syntology":null},{"url":"/paper/youtube-8m-a-large-scale-video-classification","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","date":"2016-09-27","arxiv_id":"1609.08675","repositories_listed":7,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/two-stream-convolutional-networks-for-action","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","date":"2014-06-09","arxiv_id":"1406.2199","repositories_listed":7,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":2}},{"url":"/paper/ucf101-a-dataset-of-101-human-actions-classes","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","date":"2012-12-03","arxiv_id":"1212.0402","repositories_listed":7,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/vatt-transformers-for-multimodal-self","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","date":"2021-04-22","arxiv_id":"2104.11178","repositories_listed":5,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":8}},{"url":"/paper/you-only-watch-once-a-unified-cnn","title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","date":"2019-11-15","arxiv_id":"1911.06644","repositories_listed":5,"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":2}},{"url":"/paper/representation-flow-for-action-recognition","title":"Representation Flow for Action Recognition","date":"2018-10-02","arxiv_id":"1810.01455","repositories_listed":5,"syntology":null},{"url":"/paper/temporal-relational-reasoning-in-videos","title":"Temporal Relational Reasoning in Videos","date":"2017-11-22","arxiv_id":"1711.08496","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/towards-good-practices-for-very-deep-two","title":"Towards Good Practices for Very Deep Two-Stream ConvNets","date":"2015-07-08","arxiv_id":"1507.02159","repositories_listed":5,"syntology":null},{"url":"/paper/hiera-a-hierarchical-vision-transformer","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","date":"2023-06-01","arxiv_id":"2306.00989","repositories_listed":4,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/simba-mamba-augmented-u-shiftgcn-for-skeletal","title":"Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos","date":"2024-04-11","arxiv_id":"2404.07645","repositories_listed":3,"syntology":null},{"url":"/paper/gating-revisited-deep-multi-layer-rnns-that-1","title":"Gating Revisited: Deep Multi-layer RNNs That Can Be Trained","date":"2019-11-25","arxiv_id":"1911.11033","repositories_listed":3,"syntology":null},{"url":"/paper/what-makes-training-multi-modal-networks-hard","title":"What Makes Training Multi-Modal Classification Networks Hard?","date":"2019-05-29","arxiv_id":"1905.12681","repositories_listed":3,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/r-c3d-region-convolutional-3d-network-for","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","date":"2017-03-22","arxiv_id":"1703.07814","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/video-action-recognition-collaborative","title":"Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer","date":"2023-02-17","arxiv_id":"2302.09187","repositories_listed":2,"syntology":null},{"url":"/paper/florence-a-new-foundation-model-for-computer","title":"Florence: A New Foundation Model for Computer Vision","date":"2021-11-22","arxiv_id":"2111.11432","repositories_listed":2,"syntology":null},{"url":"/paper/actionclip-a-new-paradigm-for-video-action","title":"ActionCLIP: A New Paradigm for Video Action Recognition","date":"2021-09-17","arxiv_id":"2109.08472","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/video-classification-with-finecoarse-networks","title":"Busy-Quiet Video Disentangling for Video Classification","date":"2021-03-29","arxiv_id":"2103.15584","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-3","title":"Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework","date":"2020-08-06","arxiv_id":"2008.02531","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/integralaction-pose-driven-feature","title":"IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos","date":"2020-07-13","arxiv_id":"2007.06317","repositories_listed":2,"syntology":null},{"url":"/paper/learning-video-representations-from","title":"Learning Video Representations from Correspondence Proposals","date":"2019-05-20","arxiv_id":"1905.07853","repositories_listed":2,"syntology":null},{"url":"/paper/resource-efficient-3d-convolutional-neural","title":"Resource Efficient 3D Convolutional Neural Networks","date":"2019-04-04","arxiv_id":"1904.02422","repositories_listed":2,"syntology":null},{"url":"/paper/2d3d-pose-estimation-and-action-recognition","title":"2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning","date":"2018-02-26","arxiv_id":"1802.09232","repositories_listed":2,"syntology":{"n":25,"n_ran":0,"n_unverified":25,"n_pointer_only":0}},{"url":"/paper/convolutional-two-stream-network-fusion-for","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","date":"2016-04-22","arxiv_id":"1604.06573","repositories_listed":2,"syntology":null},{"url":"/paper/action-recognition-using-visual-attention","title":"Action Recognition using Visual Attention","date":"2015-11-12","arxiv_id":"1511.04119","repositories_listed":2,"syntology":null},{"url":"/paper/body-hand-modality-expertized-networks-with","title":"Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition","date":"2025-03-19","arxiv_id":"2503.14960","repositories_listed":1,"syntology":null},{"url":"/paper/epam-net-an-efficient-pose-driven-attention","title":"EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition","date":"2024-08-10","arxiv_id":"2408.05421","repositories_listed":1,"syntology":null}],"syntology_records":14,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}