{"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/proposal-based-multiple-instance-learning-for-1","title":"Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization","arxiv_id":"2305.17861","date":"2023-05-29","proceeding":"CVPR 2023 1","authors":["Huan Ren","Wenfei Yang","Tianzhu Zhang","Yongdong Zhang"],"abstract":"Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training. Without instance-level annotations, most existing methods follow the Segment-based Multiple Instance Learning (S-MIL) framework, where the predictions of segments are supervised by the labels of videos. However, the objective for acquiring segment-level scores during training is not consistent with the target for acquiring proposal-level scores during testing, leading to suboptimal results. To deal with this problem, we propose a novel Proposal-based Multiple Instance Learning (P-MIL) framework that directly classifies the candidate proposals in both the training and testing stages, which includes three key designs: 1) a surrounding contrastive feature extraction module to suppress the discriminative short proposals by considering the surrounding contrastive information, 2) a proposal completeness evaluation module to inhibit the low-quality proposals with the guidance of the completeness pseudo labels, and 3) an instance-level rank consistency loss to achieve robust detection by leveraging the complementarity of RGB and FLOW modalities. Extensive experimental results on two challenging benchmarks including THUMOS14 and ActivityNet demonstrate the superior performance of our method.","url_abs":"https://arxiv.org/abs/2305.17861v1","url_pdf":"https://arxiv.org/pdf/2305.17861v1.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":"proposal-based-multiple-instance-learning-for-1","repo_url":"https://github.com/RenHuan1999/CVPR2023_P-MIL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"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":"P-MIL","rank_in_archive_order":6,"of":19,"metrics":{"Mean mAP":"26.5","mAP@0.5":"44.2"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-1","task":"Weakly Supervised Action Localization","dataset":"ActivityNet-1.3","model":"P-MIL","rank_in_archive_order":8,"of":17,"metrics":{"mAP@0.5":"41.8","mAP@0.5:0.95":"25.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on","task":"Weakly Supervised Action Localization","dataset":"THUMOS 2014","model":"P-MIL","rank_in_archive_order":7,"of":30,"metrics":{"mAP@0.1:0.5":"57.4","mAP@0.1:0.7":"47.0","mAP@0.5":"40.0"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-5","task":"Weakly Supervised Action Localization","dataset":"THUMOS14","model":"P-MIL","rank_in_archive_order":3,"of":12,"metrics":{"avg-mAP (0.1-0.5)":"57.4","avg-mAP (0.1:0.7)":"47.0","avg-mAP (0.3-0.7)":"38.0"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-4","task":"Weakly Supervised Action Localization","dataset":"THUMOS’14","model":"P-MIL","rank_in_archive_order":3,"of":13,"metrics":{"mAP@0.5":"40.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.17861","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}