{"url":"/task/weakly-supervised-action-localization","name":"Weakly Supervised Action Localization","slug":"weakly-supervised-action-localization","description_markdown":"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.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":55,"papers_with_code":35,"benchmarks":9,"benchmark_tables_in_archive":9,"benchmark_tables_shown":9,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/weakly-supervised-action-localization-on","slug":"weakly-supervised-action-localization-on","dataset":"THUMOS 2014","dataset_url":"/dataset/thumos14-1","rows_in_archive":30,"metrics":["mAP@0.1:0.7","mAP@0.1:0.5","mAP@0.5"],"first_row_in_archive_order":{"model":"HR-Pro","paper_title":"HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation","paper_url":"/paper/hr-pro-point-supervised-temporal-action","paper_date":"2023-08-24","arxiv_id":"2308.12608","code_links":[{"title":"pipixin321/hr-pro","url":"https://github.com/pipixin321/hr-pro"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-action-localization-on-2","slug":"weakly-supervised-action-localization-on-2","dataset":"ActivityNet-1.2","dataset_url":"/dataset/activitynet","rows_in_archive":19,"metrics":["Mean mAP","mAP@0.5"],"first_row_in_archive_order":{"model":"SAL","paper_title":"Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization","paper_url":"/paper/multilevel-semantic-and-adaptive-actionness","paper_date":"2024-11-24","arxiv_id":null,"code_links":[{"title":"lizhilin-ustc/SAL","url":"https://github.com/lizhilin-ustc/SAL"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-action-localization-on-1","slug":"weakly-supervised-action-localization-on-1","dataset":"ActivityNet-1.3","dataset_url":"/dataset/activitynet","rows_in_archive":17,"metrics":["mAP@0.5:0.95","mAP@0.5"],"first_row_in_archive_order":{"model":"SAL","paper_title":"Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization","paper_url":"/paper/multilevel-semantic-and-adaptive-actionness","paper_date":"2024-11-24","arxiv_id":null,"code_links":[{"title":"lizhilin-ustc/SAL","url":"https://github.com/lizhilin-ustc/SAL"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-action-localization-on-4","slug":"weakly-supervised-action-localization-on-4","dataset":"THUMOS’14","dataset_url":"/dataset/thumos14-1","rows_in_archive":13,"metrics":["mAP@0.5","avg-mAP (0.1-0.5)"],"first_row_in_archive_order":{"model":"LACP","paper_title":"Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization","paper_url":"/paper/learning-action-completeness-from-points-for","paper_date":"2021-08-11","arxiv_id":"2108.05029","code_links":[{"title":"Pilhyeon/Learning-Action-Completeness-from-Points","url":"https://github.com/Pilhyeon/Learning-Action-Completeness-from-Points"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-action-localization-on-5","slug":"weakly-supervised-action-localization-on-5","dataset":"THUMOS14","dataset_url":"/dataset/thumos14-1","rows_in_archive":12,"metrics":["avg-mAP (0.3-0.7)","avg-mAP (0.1:0.7)","avg-mAP (0.1-0.5)"],"first_row_in_archive_order":{"model":"HR-Pro","paper_title":"HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation","paper_url":"/paper/hr-pro-point-supervised-temporal-action","paper_date":"2023-08-24","arxiv_id":"2308.12608","code_links":[{"title":"pipixin321/hr-pro","url":"https://github.com/pipixin321/hr-pro"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-action-localization-on-gtea","slug":"weakly-supervised-action-localization-on-gtea","dataset":"GTEA","dataset_url":"/dataset/gtea","rows_in_archive":6,"metrics":["mAP@0.1:0.7","mAP@0.5"],"first_row_in_archive_order":{"model":"AU-Action","paper_title":"Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning","paper_url":"/paper/is-weakly-supervised-action-segmentation","paper_date":"2023-10-22","arxiv_id":null,"code_links":[{"title":"fandulu/DD-Net","url":"https://github.com/fandulu/DD-Net"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-action-localization-on-6","slug":"weakly-supervised-action-localization-on-6","dataset":"BEOID","dataset_url":"/dataset/beoid","rows_in_archive":5,"metrics":["mAP@0.1:0.7","mAP@0.5"],"first_row_in_archive_order":{"model":"HR-Pro","paper_title":"HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation","paper_url":"/paper/hr-pro-point-supervised-temporal-action","paper_date":"2023-08-24","arxiv_id":"2308.12608","code_links":[{"title":"pipixin321/hr-pro","url":"https://github.com/pipixin321/hr-pro"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-action-localization-on-7","slug":"weakly-supervised-action-localization-on-7","dataset":"FineAction","dataset_url":"/dataset/fineaction","rows_in_archive":4,"metrics":["mAP","mAP IOU@0.5","mAP IOU@0.75","mAP IOU@0.95"],"first_row_in_archive_order":{"model":"HAAN","paper_title":"Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions","paper_url":"/paper/weakly-supervised-temporal-action-detection","paper_date":"2022-07-24","arxiv_id":"2207.11805","code_links":[{"title":"lizhi1104/haan","url":"https://github.com/lizhi1104/haan"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-action-localization-on-8","slug":"weakly-supervised-action-localization-on-8","dataset":"THUMOS' 14","dataset_url":"/dataset/thumos14-1","rows_in_archive":1,"metrics":["avg-mAP (0.1:0.7)"],"first_row_in_archive_order":{"model":"ProCL","paper_title":"Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning","paper_url":"/paper/weakly-supervised-action-localization-via","paper_date":"2022-06-22","arxiv_id":"2206.11011","code_links":[{"title":"Run542968/ProCL","url":"https://github.com/Run542968/ProCL"},{"title":"fjchange/him-net","url":"https://github.com/fjchange/him-net"}],"syntology":null}}],"datasets":[{"url":"/dataset/activitynet","name":"ActivityNet","full_name":"","num_papers_in_archive":807},{"url":"/dataset/thumos14-1","name":"THUMOS14","full_name":"","num_papers_in_archive":318},{"url":"/dataset/gtea","name":"GTEA","full_name":"Georgia Tech Egocentric Activity","num_papers_in_archive":120},{"url":"/dataset/fineaction","name":"FineAction","full_name":"","num_papers_in_archive":24},{"url":"/dataset/beoid","name":"BEOID","full_name":"Bristol Egocentric Object Interactions Dataset","num_papers_in_archive":5}],"subtasks":[],"parent_tasks":[{"url":"/task/action-recognition","name":"Temporal Action Localization"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":35,"tagged_in_all":55,"items":[{"url":"/paper/recognition-of-instrument-tissue-interactions","title":"Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets","date":"2020-07-10","arxiv_id":"2007.05405","repositories_listed":4,"syntology":null},{"url":"/paper/videomix-rethinking-data-augmentation-for","title":"VideoMix: Rethinking Data Augmentation for Video Classification","date":"2020-12-07","arxiv_id":"2012.03457","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/weakly-supervised-action-localization-by","title":"Weakly Supervised Action Localization by Sparse Temporal Pooling Network","date":"2017-12-14","arxiv_id":"1712.05080","repositories_listed":3,"syntology":null},{"url":"/paper/hide-and-seek-forcing-a-network-to-be","title":"Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization","date":"2017-04-13","arxiv_id":"1704.04232","repositories_listed":3,"syntology":null},{"url":"/paper/weakly-supervised-action-localization-via","title":"Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning","date":"2022-06-22","arxiv_id":"2206.11011","repositories_listed":2,"syntology":null},{"url":"/paper/cross-modal-consensus-network-for-weakly","title":"Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization","date":"2021-07-27","arxiv_id":"2107.12589","repositories_listed":2,"syntology":null},{"url":"/paper/acm-net-action-context-modeling-network-for","title":"ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization","date":"2021-04-07","arxiv_id":"2104.02967","repositories_listed":2,"syntology":null},{"url":"/paper/background-modeling-via-uncertainty","title":"Weakly-supervised Temporal Action Localization by Uncertainty Modeling","date":"2020-06-12","arxiv_id":"2006.07006","repositories_listed":2,"syntology":null},{"url":"/paper/background-suppression-network-for-weakly","title":"Background Suppression Network for Weakly-supervised Temporal Action Localization","date":"2019-11-22","arxiv_id":"1911.09963","repositories_listed":2,"syntology":null},{"url":"/paper/guess-where-actor-supervision-for","title":"Guess Where? Actor-Supervision for Spatiotemporal Action Localization","date":"2018-04-05","arxiv_id":"1804.01824","repositories_listed":2,"syntology":null},{"url":"/paper/untrimmednets-for-weakly-supervised-action","title":"UntrimmedNets for Weakly Supervised Action Recognition and Detection","date":"2017-03-09","arxiv_id":"1703.03329","repositories_listed":2,"syntology":null},{"url":"/paper/multilevel-semantic-and-adaptive-actionness","title":"Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization","date":"2024-11-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-temporal-action-8","title":"Weakly supervised temporal action localization with actionness-guided false positive suppression","date":"2024-04-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-foreground-and-background-1","title":"Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach","date":"2023-12-21","arxiv_id":"2312.14138","repositories_listed":1,"syntology":null},{"url":"/paper/is-weakly-supervised-action-segmentation","title":"Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning","date":"2023-10-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hr-pro-point-supervised-temporal-action","title":"HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation","date":"2023-08-24","arxiv_id":"2308.12608","repositories_listed":1,"syntology":null},{"url":"/paper/actionness-inconsistency-guided-contrastive","title":"Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action Localization","date":"2023-06-26","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/proposal-based-multiple-instance-learning-for-1","title":"Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization","date":"2023-05-29","arxiv_id":"2305.17861","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-temporal-action-detection","title":"Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions","date":"2022-07-24","arxiv_id":"2207.11805","repositories_listed":1,"syntology":null},{"url":"/paper/convex-combination-consistency-between","title":"Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization","date":"2022-05-01","arxiv_id":"2205.00400","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-temporal-contrastive-learning","title":"Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization","date":"2022-03-31","arxiv_id":"2203.16800","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/learning-action-completeness-from-points-for","title":"Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization","date":"2021-08-11","arxiv_id":"2108.05029","repositories_listed":1,"syntology":null},{"url":"/paper/fineaction-a-fined-video-dataset-for-temporal","title":"FineAction: A Fine-Grained Video Dataset for Temporal Action Localization","date":"2021-05-24","arxiv_id":"2105.11107","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-action-selection-learning","title":"Weakly Supervised Action Selection Learning in Video","date":"2021-05-06","arxiv_id":"2105.02439","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/cola-weakly-supervised-temporal-action","title":"CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning","date":"2021-03-30","arxiv_id":"2103.16392","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-action-segmentation-from-timestamp","title":"Temporal Action Segmentation from Timestamp Supervision","date":"2021-03-11","arxiv_id":"2103.06669","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/d2-net-weakly-supervised-action-localization","title":"D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations","date":"2020-12-11","arxiv_id":"2012.06440","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-background-aware-loss-for-weakly","title":"Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization","date":"2020-07-13","arxiv_id":"2007.06643","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-action-localization-with-2","title":"Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning","date":"2020-03-31","arxiv_id":"2004.00163","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-action-localization-by-2","title":"Weakly-Supervised Action Localization by Generative Attention Modeling","date":"2020-03-27","arxiv_id":"2003.12424","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}