{"url":"/sota/skeleton-based-action-recognition-on-j-hmdb","task":{"name":"Skeleton Based Action Recognition","url":"/task/skeleton-based-action-recognition","note":null},"dataset":{"name":"J-HMDB","url":"/dataset/jhmdb"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing","Time Series"],"category_note":null,"description":"**Skeleton-based Action Recognition** is a computer vision task that involves recognizing human actions from a sequence of 3D skeletal joint data captured from sensors such as Microsoft Kinect, Intel RealSense, and wearable devices. The goal of skeleton-based action recognition is to develop algorithms that can understand and classify human actions from skeleton data, which can be used in various applications such as human-computer interaction, sports analysis, and surveillance.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [View Adaptive Neural Networks for High\r\nPerformance Skeleton-based Human Action\r\nRecognition](https://arxiv.org/pdf/1804.07453v3.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy (RGB+pose)","Accuracy (pose)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy (RGB+pose)":"higher","Accuracy (pose)":"higher"}},"counts":{"rows":13,"rows_with_code":7,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Potion","metrics":{"Accuracy (RGB+pose)":"90.4","Accuracy (pose)":"67.9"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/potion-pose-motion-representation-for-action","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Choutas_PoTion_Pose_MoTion_CVPR_2018_paper.html","paper_title":"PoTion: Pose MoTion Representation for Action Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"PA3D+RPAN","metrics":{"Accuracy (RGB+pose)":"86.1"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/pa3d-pose-action-3d-machine-for-video","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Yan_PA3D_Pose-Action_3D_Machine_for_Video_Recognition_CVPR_2019_paper.html","paper_title":"PA3D: Pose-Action 3D Machine for Video Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"I3D + Potion","metrics":{"Accuracy (RGB+pose)":"85.5"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/potion-pose-motion-representation-for-action","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Choutas_PoTion_Pose_MoTion_CVPR_2018_paper.html","paper_title":"PoTion: Pose MoTion Representation for Action Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"I3D","metrics":{"Accuracy (RGB+pose)":"84.1"},"uses_additional_data":false,"paper_date":"2017-05-22","paper":"/paper/quo-vadis-action-recognition-a-new-model-and","paper_url":"http://arxiv.org/abs/1705.07750v3","paper_title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","code":"https://github.com/open-mmlab/mmaction2","n_code_links":34,"syntology":{"n_ran":16,"n_unverified":12,"n_samples":28,"n_pointer_only_licence":7}},{"rank_in_archive_order":5,"model":"RPAN","metrics":{"Accuracy (RGB+pose)":"83.9"},"uses_additional_data":false,"paper_date":"2017-10-22","paper":"/paper/rpan-an-end-to-end-recurrent-pose-attention-1","paper_url":"https://doi.org/10.1109/ICCV.2017.402","paper_title":"RPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in Videos","code":"https://github.com/agethen/RPAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"Chained (RGB+Flow +Pose)","metrics":{"Accuracy (RGB+pose)":"76.1","Accuracy (pose)":"56.8"},"uses_additional_data":false,"paper_date":"2017-04-03","paper":"/paper/chained-multi-stream-networks-exploiting-pose","paper_url":"http://arxiv.org/abs/1704.00616v2","paper_title":"Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection","code":"https://github.com/mzolfaghari/chained-multistream-networks","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"MR Two-Sream R-CNN","metrics":{"Accuracy (RGB+pose)":"71.1"},"uses_additional_data":false,"paper_date":"2016-09-17","paper":"/paper/multi-region-two-stream-r-cnn-for-action","paper_url":"https://doi.org/10.1007/978-3-319-46493-0_45","paper_title":"Multi-region two-stream R-CNN for action detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"PA3D","metrics":{"Accuracy (RGB+pose)":"69.5"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/pa3d-pose-action-3d-machine-for-video","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Yan_PA3D_Pose-Action_3D_Machine_for_Video_Recognition_CVPR_2019_paper.html","paper_title":"PA3D: Pose-Action 3D Machine for Video Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"STAR-Net","metrics":{"Accuracy (RGB+pose)":"64.3"},"uses_additional_data":false,"paper_date":"2019-02-26","paper":"/paper/star-net-action-recognition-using-spatio","paper_url":"http://arxiv.org/abs/1902.10024v1","paper_title":"STAR-Net: Action Recognition using Spatio-Temporal Activation Reprojection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"Action Tubes","metrics":{"Accuracy (RGB+pose)":"62.5"},"uses_additional_data":false,"paper_date":"2014-11-21","paper":"/paper/finding-action-tubes","paper_url":"http://arxiv.org/abs/1411.6031v1","paper_title":"Finding Action Tubes","code":"https://github.com/JeffCHEN2017/WSSTG","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"HT-ConvNet","metrics":{"Accuracy (RGB+pose)":"-","Accuracy (pose)":"86.1"},"uses_additional_data":false,"paper_date":"2024-12-21","paper":"/paper/hierarchical-temporal-convolution-network","paper_url":"https://www.researchgate.net/publication/387230107_Hierarchical_Temporal_Convolution_Network_Towards_Privacy-Centric_Activity_Recognition","paper_title":"Hierarchical Temporal Convolution Network:Towards Privacy-Centric Activity Recognition","code":"https://github.com/Gbouna/HT-ConvNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"DD-Net","metrics":{"Accuracy (RGB+pose)":"-","Accuracy (pose)":"77.2"},"uses_additional_data":false,"paper_date":"2019-07-23","paper":"/paper/make-skeleton-based-action-recognition-model-1","paper_url":"https://arxiv.org/abs/1907.09658v8","paper_title":"Make Skeleton-based Action Recognition Model Smaller, Faster and Better","code":"https://github.com/fandulu/DD-Net","n_code_links":3,"syntology":null},{"rank_in_archive_order":13,"model":"EHPI","metrics":{"Accuracy (RGB+pose)":"-","Accuracy (pose)":"65.5"},"uses_additional_data":false,"paper_date":"2019-04-19","paper":"/paper/simple-yet-efficient-real-time-pose-based","paper_url":"http://arxiv.org/abs/1904.09140v1","paper_title":"Simple yet efficient real-time pose-based action recognition","code":"https://github.com/noboevbo/ehpi_action_recognition","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 7,081 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":16,"n_unverified":12,"n_samples":28,"n_pointer_only_licence":7,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":16,"n_unverified":12,"n_samples":28,"n_pointer_only_licence":7,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}