{"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/enhancing-temporal-action-localization","title":"Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism","arxiv_id":"2407.13078","date":"2024-07-18","proceeding":null,"authors":["Sangyoun Lee","Juho Jung","Changdae Oh","Sunghee Yun"],"abstract":"Temporal Action Localization (TAL) is a critical task in video analysis, identifying precise start and end times of actions. Existing methods like CNNs, RNNs, GCNs, and Transformers have limitations in capturing long-range dependencies and temporal causality. To address these challenges, we propose a novel TAL architecture leveraging the Selective State Space Model (S6). Our approach integrates the Feature Aggregated Bi-S6 block, Dual Bi-S6 structure, and a recurrent mechanism to enhance temporal and channel-wise dependency modeling without increasing parameter complexity. Extensive experiments on benchmark datasets demonstrate state-of-the-art results with mAP scores of 74.2% on THUMOS-14, 42.9% on ActivityNet, 29.6% on FineAction, and 45.8% on HACS. Ablation studies validate our method's effectiveness, showing that the Dual structure in the Stem module and the recurrent mechanism outperform traditional approaches. Our findings demonstrate the potential of S6-based models in TAL tasks, paving the way for future research.","url_abs":"https://arxiv.org/abs/2407.13078v1","url_pdf":"https://arxiv.org/pdf/2407.13078v1.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":"enhancing-temporal-action-localization","repo_url":"https://github.com/lsy0882/RDFA-S6","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/temporal-action-localization-on-activitynet","task":"Temporal Action Localization","dataset":"ActivityNet-1.3","model":"RDFA-S6 (InternVideo2-6B)","rank_in_archive_order":1,"of":33,"metrics":{"mAP":"42.9","mAP IOU@0.5":"64.1","mAP IOU@0.75":"44.0","mAP IOU@0.95":"10.6"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-fineaction","task":"Temporal Action Localization","dataset":"FineAction","model":"RDFA-S6 (InternVideo2-6B)","rank_in_archive_order":1,"of":9,"metrics":{"mAP":"29.6","mAP IOU@0.5":"46.4","mAP IOU@0.75":"29.5","mAP IOU@0.95":"7.6"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-hacs","task":"Temporal Action Localization","dataset":"HACS","model":"RDFA-S6 (InternVideo2-6B)","rank_in_archive_order":1,"of":12,"metrics":{"Average-mAP":"45.8","mAP@0.5":"66.4","mAP@0.75":"47.2","mAP@0.95":"14.3"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-thumos14","task":"Temporal Action Localization","dataset":"THUMOS’14","model":"RDFA-S6 (InternVideo2-6B)","rank_in_archive_order":2,"of":42,"metrics":{"Avg mAP (0.3:0.7)":"74.2","mAP IOU@0.3":"88.7","mAP IOU@0.4":"84.6","mAP IOU@0.5":"78.2","mAP IOU@0.6":"66.6","mAP IOU@0.7":"51.9"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}