{"url":"/sota/activity-recognition-on-rwf-2000","task":{"name":"Activity Recognition","url":"/task/activity-recognition","note":null},"dataset":{"name":"RWF-2000","url":"/dataset/rwf-2000"},"category":"Computer Vision","categories":["Computer Vision","Robots","Time Series"],"category_note":null,"description":"Human **Activity Recognition** is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.\n\n\n<span class=\"description-source\">Source: [Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters ](https://arxiv.org/abs/1605.08140)</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":5,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"Structured Keypoint Pooling","metrics":{"Accuracy":"93.4"},"uses_additional_data":true,"paper_date":"2023-03-27","paper":"/paper/unified-keypoint-based-action-recognition","paper_url":"https://arxiv.org/abs/2303.15270v1","paper_title":"Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Semi-Supervised Hard Attention (SSHA); pretrained on Deepmind Kinetics dataset","metrics":{"Accuracy":"90.4"},"uses_additional_data":true,"paper_date":"2022-02-04","paper":"/paper/video-violence-recognition-and-localization","paper_url":"https://arxiv.org/abs/2202.02212v4","paper_title":"Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Human Skeletons + Change Detection","metrics":{"Accuracy":"90.25"},"uses_additional_data":false,"paper_date":"2023-05-20","paper":"/paper/human-skeletons-and-change-detection-for","paper_url":"https://www.sciencedirect.com/science/article/pii/S1077314223001194","paper_title":"Human skeletons and change detection for efficient violence detection in surveillance videos","code":"https://github.com/atmguille/Violence-Detection-With-Human-Skeletons","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Separable Convolutional LSTM","metrics":{"Accuracy":"89.75"},"uses_additional_data":false,"paper_date":"2021-02-21","paper":"/paper/efficient-two-stream-network-for-violence","paper_url":"https://arxiv.org/abs/2102.10590v3","paper_title":"Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM","code":"https://github.com/Zedd1558/TwoStreamSepConvLSTM_ViolenceDetection","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"SPIL Convolution","metrics":{"Accuracy":"89.3"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/human-interaction-learning-on-3d-skeleton","paper_url":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/1526_ECCV_2020_paper.php","paper_title":"Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"Flow Gated Network","metrics":{"Accuracy":"87.25"},"uses_additional_data":false,"paper_date":"2019-11-14","paper":"/paper/rwf-2000-an-open-large-scale-video-database","paper_url":"https://arxiv.org/abs/1911.05913v3","paper_title":"RWF-2000: An Open Large Scale Video Database for Violence Detection","code":"https://github.com/mchengny/RWF2000-Video-Database-for-Violence-Detection","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 6,885 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":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"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":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"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":0,"n_unverified":0,"n_samples":0,"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"}}}