{"url":"/sota/group-activity-recognition-on-collective","task":{"name":"Group Activity Recognition","url":"/task/group-activity-recognition","note":null},"dataset":{"name":"Collective Activity","url":"/dataset/collective-activity"},"category":"Computer Vision","categories":["Computer Vision","Robots","Time Series"],"category_note":null,"description":"**Group Activity Recognition** is a subset of human activity recognition problem which focuses on the collective behavior of a group of people, resulted from the individual actions of the persons and their interactions. Collective activity recognition is a basic task for automatic human behavior analysis in many areas like surveillance or sports videos.\n\n\n<span class=\"description-source\">Source: [A Multi-Stream Convolutional Neural Network Framework for Group Activity Recognition ](https://arxiv.org/abs/1812.10328)</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"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":6,"rows_with_code":3,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"Tamura et al.","metrics":{"Accuracy":"96.5"},"uses_additional_data":true,"paper_date":"2022-07-12","paper":"/paper/hunting-group-clues-with-transformers-for","paper_url":"https://arxiv.org/abs/2207.05254v1","paper_title":"Hunting Group Clues with Transformers for Social Group Activity Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"COMPOSER","metrics":{"Accuracy":"96.2"},"uses_additional_data":false,"paper_date":"2021-12-11","paper":"/paper/composer-compositional-learning-of-group","paper_url":"https://arxiv.org/abs/2112.05892v3","paper_title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","code":"https://github.com/hongluzhou/composer","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"GT (Inception-v3)","metrics":{"Accuracy":"91"},"uses_additional_data":false,"paper_date":"2019-04-23","paper":"/paper/learning-actor-relation-graphs-for-group","paper_url":"http://arxiv.org/abs/1904.10117v1","paper_title":"Learning Actor Relation Graphs for Group Activity Recognition","code":"https://github.com/wjchaoGit/Group-Activity-Recognition","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"CHASE(CTR-GCN)","metrics":{"Accuracy":"89.61"},"uses_additional_data":false,"paper_date":"2024-10-09","paper":"/paper/chase-learning-convex-hull-adaptive-shift-for","paper_url":"https://arxiv.org/abs/2410.07153v2","paper_title":"CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition","code":"https://github.com/Necolizer/CHASE","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"H-LSTCM","metrics":{"Accuracy":"83.75"},"uses_additional_data":false,"paper_date":"2018-11-01","paper":"/paper/hierarchical-long-short-term-concurrent","paper_url":"http://arxiv.org/abs/1811.00270v1","paper_title":"Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"Deng et al.","metrics":{"Accuracy":"81.2"},"uses_additional_data":false,"paper_date":"2015-11-13","paper":"/paper/structure-inference-machines-recurrent-neural","paper_url":"http://arxiv.org/abs/1511.04196v2","paper_title":"Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition","code":null,"n_code_links":0,"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 6,264 of the 9,581 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":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+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":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"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"}}}