{"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/3c-net-category-count-and-center-loss-for","title":"3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization","arxiv_id":"1908.08216","date":"2019-08-22","proceeding":"ICCV 2019 10","authors":["Sanath Narayan","Hisham Cholakkal","Fahad Shahbaz Khan","Ling Shao"],"abstract":"Temporal action localization is a challenging computer vision problem with numerous real-world applications. Most existing methods require laborious frame-level supervision to train action localization models. In this work, we propose a framework, called 3C-Net, which only requires video-level supervision (weak supervision) in the form of action category labels and the corresponding count. We introduce a novel formulation to learn discriminative action features with enhanced localization capabilities. Our joint formulation has three terms: a classification term to ensure the separability of learned action features, an adapted multi-label center loss term to enhance the action feature discriminability and a counting loss term to delineate adjacent action sequences, leading to improved localization. Comprehensive experiments are performed on two challenging benchmarks: THUMOS14 and ActivityNet 1.2. Our approach sets a new state-of-the-art for weakly-supervised temporal action localization on both datasets. On the THUMOS14 dataset, the proposed method achieves an absolute gain of 4.6% in terms of mean average precision (mAP), compared to the state-of-the-art. Source code is available at https://github.com/naraysa/3c-net.","url_abs":"https://arxiv.org/abs/1908.08216v2","url_pdf":"https://arxiv.org/pdf/1908.08216v2.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":"3c-net-category-count-and-center-loss-for","repo_url":"https://github.com/naraysa/3c-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"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/action-classification-on-activitynet-12","task":"Action Classification","dataset":"ActivityNet-1.2","model":"3C-Net","rank_in_archive_order":2,"of":3,"metrics":{"mAP":"92.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-thumos-14","task":"Action Classification","dataset":"THUMOS'14","model":"3C-Net","rank_in_archive_order":1,"of":1,"metrics":{"mAP":"86.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-thumos14","task":"Action Classification","dataset":"THUMOS’14","model":"3C-Net","rank_in_archive_order":1,"of":3,"metrics":{"mAP":"86.9"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-2","task":"Weakly Supervised Action Localization","dataset":"ActivityNet-1.2","model":"3C-Net","rank_in_archive_order":13,"of":19,"metrics":{"Mean mAP":"21.7","mAP@0.5":"37.2"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on","task":"Weakly Supervised Action Localization","dataset":"THUMOS 2014","model":"3C-Net","rank_in_archive_order":24,"of":30,"metrics":{"mAP@0.5":"26.6"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-4","task":"Weakly Supervised Action Localization","dataset":"THUMOS’14","model":"3C-Net","rank_in_archive_order":13,"of":13,"metrics":{"mAP@0.5":"26.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.08216","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}