{"url":"/sota/temporal-action-localization-on-multithumos-1","task":{"name":"Temporal Action Localization","url":"/task/action-recognition","note":null},"dataset":{"name":"MultiTHUMOS","url":"/dataset/multithumos"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Temporal Action Localization aims to detect activities in the video stream and  output beginning and end timestamps. It is closely related to  Temporal Action Proposal Generation.","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":["Average mAP","mAP IOU@0.1","mAP IOU@0.2","mAP IOU@0.3","mAP IOU@0.4","mAP IOU@0.5","mAP IOU@0.6","mAP IOU@0.7","mAP IOU@0.8","mAP IOU@0.9"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average mAP":"higher","mAP IOU@0.1":"higher","mAP IOU@0.2":"higher","mAP IOU@0.3":"higher","mAP IOU@0.4":"higher","mAP IOU@0.5":"higher","mAP IOU@0.6":"higher","mAP IOU@0.7":"higher","mAP IOU@0.8":"higher","mAP IOU@0.9":"higher"}},"counts":{"rows":8,"rows_with_code":7,"rows_with_paper_page":8,"rows_dated":8,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"TriDet (VideoMAEv2)","metrics":{"Average mAP":"37.5","mAP IOU@0.2":"57.7","mAP IOU@0.5":"42.7","mAP IOU@0.7":"24.3"},"uses_additional_data":false,"paper_date":"2023-09-11","paper":"/paper/temporal-action-localization-with-enhanced","paper_url":"https://arxiv.org/abs/2309.05590v1","paper_title":"Temporal Action Localization with Enhanced Instant Discriminability","code":"https://github.com/dingfengshi/tridet","n_code_links":3,"syntology":null},{"rank_in_archive_order":2,"model":"DualDETR (I3D-rgb)","metrics":{"Average mAP":"32.64","mAP IOU@0.1":"53.42","mAP IOU@0.3":"47.41","mAP IOU@0.5":"35.18","mAP IOU@0.7":"20.18","mAP IOU@0.9":"4.02"},"uses_additional_data":false,"paper_date":"2024-03-31","paper":"/paper/dual-detrs-for-multi-label-temporal-action","paper_url":"https://arxiv.org/abs/2404.00653v1","paper_title":"Dual DETRs for Multi-Label Temporal Action Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"TriDet (I3D-rgb)","metrics":{"Average mAP":"30.7","mAP IOU@0.2":"49.1","mAP IOU@0.5":"34.3","mAP IOU@0.7":"17.8"},"uses_additional_data":false,"paper_date":"2023-09-11","paper":"/paper/temporal-action-localization-with-enhanced","paper_url":"https://arxiv.org/abs/2309.05590v1","paper_title":"Temporal Action Localization with Enhanced Instant Discriminability","code":"https://github.com/dingfengshi/tridet","n_code_links":3,"syntology":null},{"rank_in_archive_order":4,"model":"TemporalMaxer","metrics":{"Average mAP":"29.9","mAP IOU@0.1":"49.1","mAP IOU@0.2":"47.5","mAP IOU@0.3":"44.3","mAP IOU@0.4":"39.4","mAP IOU@0.5":"33.4","mAP IOU@0.6":"26.5","mAP IOU@0.7":"17.4","mAP IOU@0.8":"9.1","mAP IOU@0.9":"2.24"},"uses_additional_data":false,"paper_date":"2023-03-16","paper":"/paper/temporalmaxer-maximize-temporal-context-with","paper_url":"https://arxiv.org/abs/2303.09055v1","paper_title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","code":"https://github.com/tuantng/temporalmaxer","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"PointTAD","metrics":{"Average mAP":"23.5","mAP IOU@0.1":"42.3","mAP IOU@0.2":"39.7 ","mAP IOU@0.3":"35.8","mAP IOU@0.4":"30.9","mAP IOU@0.5":"24.9","mAP IOU@0.6":"18.5","mAP IOU@0.7":"12.0","mAP IOU@0.8":"5.6","mAP IOU@0.9":"1.4"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/pointtad-multi-label-temporal-action","paper_url":"https://arxiv.org/abs/2210.11035v3","paper_title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","code":"https://github.com/mcg-nju/pointtad","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"PDAN","metrics":{"Average mAP":"17.3"},"uses_additional_data":false,"paper_date":"2021-01-05","paper":"/paper/pdan-pyramid-dilated-attention-network-for","paper_url":"https://openaccess.thecvf.com/content/WACV2021/html/Dai_PDAN_Pyramid_Dilated_Attention_Network_for_Action_Detection_WACV_2021_paper.html","paper_title":"PDAN: Pyramid Dilated Attention Network for Action Detection","code":"https://github.com/dairui01/PDAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"MS-TCT","metrics":{"Average mAP":"16.2"},"uses_additional_data":false,"paper_date":"2021-12-07","paper":"/paper/ms-tct-multi-scale-temporal-convtransformer","paper_url":"https://arxiv.org/abs/2112.03902v2","paper_title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","code":"https://github.com/dairui01/MS-TCT","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":8,"model":"MLAD","metrics":{"Average mAP":"14.2"},"uses_additional_data":false,"paper_date":"2021-03-04","paper":"/paper/modeling-multi-label-action-dependencies-for","paper_url":"https://arxiv.org/abs/2103.03027v3","paper_title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","code":"https://github.com/ptirupat/MLAD","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":5}}],"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 6,795 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":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"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":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":12,"n_unverified":2,"n_samples":14,"n_pointer_only_licence":6,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":12,"n_unverified":2,"n_samples":14,"n_pointer_only_licence":6,"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"}}}