{"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/hear-me-out-fusional-approaches-for-audio","title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","arxiv_id":"2106.14118","date":"2021-06-27","proceeding":null,"authors":["Anurag Bagchi","Jazib Mahmood","Dolton Fernandes","Ravi Kiran Sarvadevabhatla"],"abstract":"State of the art architectures for untrimmed video Temporal Action Localization (TAL) have only considered RGB and Flow modalities, leaving the information-rich audio modality totally unexploited. Audio fusion has been explored for the related but arguably easier problem of trimmed (clip-level) action recognition. However, TAL poses a unique set of challenges. In this paper, we propose simple but effective fusion-based approaches for TAL. To the best of our knowledge, our work is the first to jointly consider audio and video modalities for supervised TAL. We experimentally show that our schemes consistently improve performance for state of the art video-only TAL approaches. Specifically, they help achieve new state of the art performance on large-scale benchmark datasets - ActivityNet-1.3 (54.34 mAP@0.5) and THUMOS14 (57.18 mAP@0.5). Our experiments include ablations involving multiple fusion schemes, modality combinations and TAL architectures. Our code, models and associated data are available at https://github.com/skelemoa/tal-hmo.","url_abs":"https://arxiv.org/abs/2106.14118v4","url_pdf":"https://arxiv.org/pdf/2106.14118v4.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":"hear-me-out-fusional-approaches-for-audio","repo_url":"https://github.com/skelemoa/tal-hmo","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":"action-recognition-in-videos","task_name":"Action Recognition"},{"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":"AVFusion","rank_in_archive_order":12,"of":33,"metrics":{"mAP":"36.82","mAP IOU@0.5":"54.34","mAP IOU@0.75":"37.66","mAP IOU@0.95":"8.93"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-thumos-14","task":"Temporal Action Localization","dataset":"THUMOS'14","model":"AVFusion","rank_in_archive_order":1,"of":1,"metrics":{"mAP IOU@0.5":"57.18"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-thumos14","task":"Temporal Action Localization","dataset":"THUMOS’14","model":"AVFusion","rank_in_archive_order":22,"of":42,"metrics":{"Avg mAP (0.3:0.7)":"53.3","mAP IOU@0.3":"70.1","mAP IOU@0.4":"64.9","mAP IOU@0.5":"57.1","mAP IOU@0.6":"45.4","mAP IOU@0.7":"28.8"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2106.14118","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}