{"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/slow-fast-auditory-streams-for-audio","title":"Slow-Fast Auditory Streams For Audio Recognition","arxiv_id":"2103.03516","date":"2021-03-05","proceeding":null,"authors":["Evangelos Kazakos","Arsha Nagrani","Andrew Zisserman","Dima Damen"],"abstract":"We propose a two-stream convolutional network for audio recognition, that operates on time-frequency spectrogram inputs. Following similar success in visual recognition, we learn Slow-Fast auditory streams with separable convolutions and multi-level lateral connections. The Slow pathway has high channel capacity while the Fast pathway operates at a fine-grained temporal resolution. We showcase the importance of our two-stream proposal on two diverse datasets: VGG-Sound and EPIC-KITCHENS-100, and achieve state-of-the-art results on both.","url_abs":"https://arxiv.org/abs/2103.03516v1","url_pdf":"https://arxiv.org/pdf/2103.03516v1.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":"slow-fast-auditory-streams-for-audio","repo_url":"https://github.com/ekazakos/auditory-slow-fast","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"slow-fast-auditory-streams-for-audio","repo_url":"https://github.com/porcelluscavia/audio-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"human-interaction-recognition","task_name":"Human Interaction Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-interaction-recognition-on-epic-sounds","task":"Human Interaction Recognition","dataset":"EPIC-SOUNDS","model":"Slow-Fast(Finetune by Fivewin team)","rank_in_archive_order":1,"of":1,"metrics":{"Top-1 accuracy %":"55.11"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.03516","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}