{"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/weakly-supervised-temporal-action-detection","title":"Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions","arxiv_id":"2207.11805","date":"2022-07-24","proceeding":null,"authors":["Zhi Li","Lu He","Huijuan Xu"],"abstract":"Action understanding has evolved into the era of fine granularity, as most human behaviors in real life have only minor differences. To detect these fine-grained actions accurately in a label-efficient way, we tackle the problem of weakly-supervised fine-grained temporal action detection in videos for the first time. Without the careful design to capture subtle differences between fine-grained actions, previous weakly-supervised models for general action detection cannot perform well in the fine-grained setting. We propose to model actions as the combinations of reusable atomic actions which are automatically discovered from data through self-supervised clustering, in order to capture the commonality and individuality of fine-grained actions. The learnt atomic actions, represented by visual concepts, are further mapped to fine and coarse action labels leveraging the semantic label hierarchy. Our approach constructs a visual representation hierarchy of four levels: clip level, atomic action level, fine action class level and coarse action class level, with supervision at each level. Extensive experiments on two large-scale fine-grained video datasets, FineAction and FineGym, show the benefit of our proposed weakly-supervised model for fine-grained action detection, and it achieves state-of-the-art results.","url_abs":"https://arxiv.org/abs/2207.11805v1","url_pdf":"https://arxiv.org/pdf/2207.11805v1.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":"weakly-supervised-temporal-action-detection","repo_url":"https://github.com/lizhi1104/haan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"action-understanding","task_name":"Action Understanding"},{"task_slug":"fine-grained-action-detection","task_name":"Fine-Grained Action Detection"},{"task_slug":"weakly-supervised-action-localization","task_name":"Weakly Supervised Action Localization"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-action-localization-on-7","task":"Weakly Supervised Action Localization","dataset":"FineAction","model":"HAAN","rank_in_archive_order":1,"of":4,"metrics":{"mAP":"4.10","mAP IOU@0.5":"7.05","mAP IOU@0.75":"3.95","mAP IOU@0.95":"1.14"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.11805","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}