{"url":"/sota/weakly-supervised-action-localization-on-2","task":{"name":"Weakly Supervised Action Localization","url":"/task/weakly-supervised-action-localization","note":null},"dataset":{"name":"ActivityNet-1.2","url":"/dataset/activitynet"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"In this task, the training data consists of videos with a list of activities in them without any temporal boundary annotations. However, while testing, given a video, the algorithm should recognize the activities in the video and also provide the start and end time.","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":["Mean mAP","mAP@0.5"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Mean mAP":"higher","mAP@0.5":"higher"}},"counts":{"rows":19,"rows_with_code":16,"rows_with_paper_page":19,"rows_dated":19,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SAL","metrics":{"Mean mAP":"30.8","mAP@0.5":"48.5"},"uses_additional_data":false,"paper_date":"2024-11-24","paper":"/paper/multilevel-semantic-and-adaptive-actionness","paper_url":"https://www.sciencedirect.com/science/article/pii/S0893608024008347?dgcid=coauthor","paper_title":"Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization","code":"https://github.com/lizhilin-ustc/SAL","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"AICL","metrics":{"Mean mAP":"29.9","mAP@0.5":"49.6"},"uses_additional_data":false,"paper_date":"2023-06-26","paper":"/paper/actionness-inconsistency-guided-contrastive","paper_url":"https://ojs.aaai.org/index.php/AAAI/article/view/25237","paper_title":"Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action Localization","code":"https://github.com/lizhilin-ustc/AAAI2023-AICL","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"AFPS","metrics":{"Mean mAP":"29.9","mAP@0.5":"48.6"},"uses_additional_data":false,"paper_date":"2024-04-15","paper":"/paper/weakly-supervised-temporal-action-8","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0893608024002314","paper_title":"Weakly supervised temporal action localization with actionness-guided false positive suppression","code":"https://github.com/lizhilin-ustc/AFPS","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CASE","metrics":{"Mean mAP":"27.9","mAP@0.5":"43.8"},"uses_additional_data":false,"paper_date":"2023-12-21","paper":"/paper/revisiting-foreground-and-background-1","paper_url":"https://arxiv.org/abs/2312.14138v1","paper_title":"Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach","code":"https://github.com/qinying-liu/case","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"LACP","metrics":{"Mean mAP":"26.8","mAP@0.5":"44"},"uses_additional_data":false,"paper_date":"2021-08-11","paper":"/paper/learning-action-completeness-from-points-for","paper_url":"https://arxiv.org/abs/2108.05029v1","paper_title":"Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization","code":"https://github.com/Pilhyeon/Learning-Action-Completeness-from-Points","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"P-MIL","metrics":{"Mean mAP":"26.5","mAP@0.5":"44.2"},"uses_additional_data":false,"paper_date":"2023-05-29","paper":"/paper/proposal-based-multiple-instance-learning-for-1","paper_url":"https://arxiv.org/abs/2305.17861v1","paper_title":"Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization","code":"https://github.com/RenHuan1999/CVPR2023_P-MIL","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"CoLA","metrics":{"Mean mAP":"26.1","mAP@0.5":"42.7"},"uses_additional_data":false,"paper_date":"2021-03-30","paper":"/paper/cola-weakly-supervised-temporal-action","paper_url":"https://arxiv.org/abs/2103.16392v2","paper_title":"CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning","code":"https://github.com/zhang-can/CoLA","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"D2-Net","metrics":{"Mean mAP":"26","mAP@0.5":"42.3"},"uses_additional_data":false,"paper_date":"2020-12-11","paper":"/paper/d2-net-weakly-supervised-action-localization","paper_url":"https://arxiv.org/abs/2012.06440v2","paper_title":"D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations","code":"https://github.com/naraysa/D2-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"Lee et al.","metrics":{"Mean mAP":"25.9","mAP@0.5":"41.2"},"uses_additional_data":false,"paper_date":"2020-06-12","paper":"/paper/background-modeling-via-uncertainty","paper_url":"https://arxiv.org/abs/2006.07006v3","paper_title":"Weakly-supervised Temporal Action Localization by Uncertainty Modeling","code":"https://github.com/Pilhyeon/WTAL-Uncertainty-Modeling","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"ASL","metrics":{"Mean mAP":"25.8","mAP@0.5":"40.2"},"uses_additional_data":false,"paper_date":"2021-05-06","paper":"/paper/weakly-supervised-action-selection-learning","paper_url":"https://arxiv.org/abs/2105.02439v1","paper_title":"Weakly Supervised Action Selection Learning in Video","code":"https://github.com/layer6ai-labs/ASL","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":11,"model":"DGAM","metrics":{"Mean mAP":"24.4","mAP@0.5":"41.0"},"uses_additional_data":false,"paper_date":"2020-03-27","paper":"/paper/weakly-supervised-action-localization-by-2","paper_url":"https://arxiv.org/abs/2003.12424v2","paper_title":"Weakly-Supervised Action Localization by Generative Attention Modeling","code":"https://github.com/bfshi/DGAM-Weakly-Supervised-Action-Localization","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"SF-Net","metrics":{"Mean mAP":"22.8","mAP@0.5":"37.8"},"uses_additional_data":false,"paper_date":"2020-03-15","paper":"/paper/sf-net-single-frame-supervision-for-temporal","paper_url":"https://arxiv.org/abs/2003.06845v6","paper_title":"SF-Net: Single-Frame Supervision for Temporal Action Localization","code":"https://github.com/Flowerfan/SF-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"3C-Net","metrics":{"Mean mAP":"21.7","mAP@0.5":"37.2"},"uses_additional_data":false,"paper_date":"2019-08-22","paper":"/paper/3c-net-category-count-and-center-loss-for","paper_url":"https://arxiv.org/abs/1908.08216v2","paper_title":"3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization","code":"https://github.com/naraysa/3c-net","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"BaS-Net","metrics":{"mAP@0.5":"38.5"},"uses_additional_data":false,"paper_date":"2019-11-22","paper":"/paper/background-suppression-network-for-weakly","paper_url":"https://arxiv.org/abs/1911.09963v1","paper_title":"Background Suppression Network for Weakly-supervised Temporal Action Localization","code":"https://github.com/Pilhyeon/BaSNet-pytorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"CleanNet","metrics":{"mAP@0.5":"37.1"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/weakly-supervised-temporal-action","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Weakly_Supervised_Temporal_Action_Localization_Through_Contrast_Based_Evaluation_Networks_ICCV_2019_paper.html","paper_title":"Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"W-TALC","metrics":{"mAP@0.5":"37.0"},"uses_additional_data":false,"paper_date":"2018-07-27","paper":"/paper/w-talc-weakly-supervised-temporal-activity","paper_url":"http://arxiv.org/abs/1807.10418v3","paper_title":"W-TALC: Weakly-supervised Temporal Activity Localization and Classification","code":"https://github.com/sujoyp/wtalc-pytorch","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"CMCS","metrics":{"mAP@0.5":"36.8"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/completeness-modeling-and-context-separation","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Completeness_Modeling_and_Context_Separation_for_Weakly_Supervised_Temporal_Action_CVPR_2019_paper.html","paper_title":"Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization","code":"https://github.com/Finspire13/CMCS-Temporal-Action-Localization","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"TSM","metrics":{"mAP@0.5":"28.3"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/temporal-structure-mining-for-weakly","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Yu_Temporal_Structure_Mining_for_Weakly_Supervised_Action_Detection_ICCV_2019_paper.html","paper_title":"Temporal Structure Mining for Weakly Supervised Action Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"AutoLoc","metrics":{"mAP@0.5":"27.3"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/autoloc-weakly-supervised-temporal-action-1","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Zheng_Shou_AutoLoc_Weakly-supervised_Temporal_ECCV_2018_paper.html","paper_title":"AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos","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":2,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":1,"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"}}}