{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/background-suppression-network-for-weakly","title":"Background Suppression Network for Weakly-supervised Temporal Action Localization","arxiv_id":"1911.09963","date":"2019-11-22","proceeding":null,"authors":["Pilhyeon Lee","Youngjung Uh","Hyeran Byun"],"abstract":"Weakly-supervised temporal action localization is a very challenging problem because frame-wise labels are not given in the training stage while the only hint is video-level labels: whether each video contains action frames of interest. Previous methods aggregate frame-level class scores to produce video-level prediction and learn from video-level action labels. This formulation does not fully model the problem in that background frames are forced to be misclassified as action classes to predict video-level labels accurately. In this paper, we design Background Suppression Network (BaS-Net) which introduces an auxiliary class for background and has a two-branch weight-sharing architecture with an asymmetrical training strategy. This enables BaS-Net to suppress activations from background frames to improve localization performance. Extensive experiments demonstrate the effectiveness of BaS-Net and its superiority over the state-of-the-art methods on the most popular benchmarks - THUMOS'14 and ActivityNet. Our code and the trained model are available at https://github.com/Pilhyeon/BaSNet-pytorch.","url_abs":"https://arxiv.org/abs/1911.09963v1","url_pdf":"https://arxiv.org/pdf/1911.09963v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"background-suppression-network-for-weakly","repo_url":"https://github.com/Pilhyeon/BaSNet-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"background-suppression-network-for-weakly","repo_url":"https://github.com/Pilhyeon/Learning-Action-Completeness-from-Points","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"weakly-supervised-action-localization","task_name":"Weakly Supervised Action Localization"},{"task_slug":"weakly-supervised-temporal-action","task_name":"Weakly-supervised Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-action-localization-on-2","task":"Weakly Supervised Action Localization","dataset":"ActivityNet-1.2","model":"BaS-Net","rank_in_archive_order":14,"of":19,"metrics":{"mAP@0.5":"38.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-1","task":"Weakly Supervised Action Localization","dataset":"ActivityNet-1.3","model":"BaS-Net","rank_in_archive_order":13,"of":17,"metrics":{"mAP@0.5":"34.5","mAP@0.5:0.95":"22.2"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on","task":"Weakly Supervised Action Localization","dataset":"THUMOS 2014","model":"BaS-Net","rank_in_archive_order":19,"of":30,"metrics":{"mAP@0.1:0.5":"43.6","mAP@0.1:0.7":"35.3","mAP@0.5":"27"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-4","task":"Weakly Supervised Action Localization","dataset":"THUMOS’14","model":"BasNet","rank_in_archive_order":12,"of":13,"metrics":{"mAP@0.5":"27.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.09963","atlas_url":"https://app.syntology.ai/?focus=1911.09963","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}