{"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/ca-2st-cross-attention-in-audio-space-and","title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","arxiv_id":"2503.23447","date":"2025-03-30","proceeding":null,"authors":["Jongseo Lee","Joohyun Chang","DongHo Lee","Jinwoo Choi"],"abstract":"We propose Cross-Attention in Audio, Space, and Time (CA^2ST), a transformer-based method for holistic video recognition. Recognizing actions in videos requires both spatial and temporal understanding, yet most existing models lack a balanced spatio-temporal understanding of videos. To address this, we propose a novel two-stream architecture, called Cross-Attention in Space and Time (CAST), using only RGB input. In each layer of CAST, Bottleneck Cross-Attention (B-CA) enables spatial and temporal experts to exchange information and make synergistic predictions. For holistic video understanding, we extend CAST by integrating an audio expert, forming Cross-Attention in Visual and Audio (CAVA). We validate the CAST on benchmarks with different characteristics, EPIC-KITCHENS-100, Something-Something-V2, and Kinetics-400, consistently showing balanced performance. We also validate the CAVA on audio-visual action recognition benchmarks, including UCF-101, VGG-Sound, KineticsSound, and EPIC-SOUNDS. With a favorable performance of CAVA across these datasets, we demonstrate the effective information exchange among multiple experts within the B-CA module. In summary, CA^2ST combines CAST and CAVA by employing spatial, temporal, and audio experts through cross-attention, achieving balanced and holistic video understanding.","url_abs":"https://arxiv.org/abs/2503.23447v1","url_pdf":"https://arxiv.org/pdf/2503.23447v1.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":[],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"video-recognition","task_name":"Video Recognition"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-sounds","task":"Action Classification","dataset":"Kinetics-Sounds","model":"CA2ST(B/16)","rank_in_archive_order":1,"of":4,"metrics":{"Top 1 Accuracy":"93.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-sounds","task":"Action Classification","dataset":"Kinetics-Sounds","model":"CAVA(B/16)","rank_in_archive_order":2,"of":4,"metrics":{"Top 1 Accuracy":"92.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-ucf101","task":"Action Recognition","dataset":"UCF101","model":"CA2ST(B/16)","rank_in_archive_order":22,"of":91,"metrics":{"3-fold Accuracy":"97.2"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-epic-sounds","task":"Audio Classification","dataset":"EPIC-SOUNDS","model":"CA2ST(B/16)","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"61"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-epic-sounds","task":"Audio Classification","dataset":"EPIC-SOUNDS","model":"CAVA(B/16)","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"60.3"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-vggsound","task":"Audio Classification","dataset":"VGGSound","model":"CA2ST(B/16)","rank_in_archive_order":2,"of":23,"metrics":{"Top 1 Accuracy":"68.3"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-vggsound","task":"Audio Classification","dataset":"VGGSound","model":"CAVA(B/16)","rank_in_archive_order":4,"of":23,"metrics":{"Top 1 Accuracy":"68.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}