{"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/audio-visual-scene-analysis-with-self","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","arxiv_id":"1804.03641","date":"2018-04-10","proceeding":"ECCV 2018 9","authors":["Andrew Owens","Alexei A. Efros"],"abstract":"The thud of a bouncing ball, the onset of speech as lips open -- when visual\nand audio events occur together, it suggests that there might be a common,\nunderlying event that produced both signals. In this paper, we argue that the\nvisual and audio components of a video signal should be modeled jointly using a\nfused multisensory representation. We propose to learn such a representation in\na self-supervised way, by training a neural network to predict whether video\nframes and audio are temporally aligned. We use this learned representation for\nthree applications: (a) sound source localization, i.e. visualizing the source\nof sound in a video; (b) audio-visual action recognition; and (c) on/off-screen\naudio source separation, e.g. removing the off-screen translator's voice from a\nforeign official's speech. Code, models, and video results are available on our\nwebpage: http://andrewowens.com/multisensory","url_abs":"http://arxiv.org/abs/1804.03641v2","url_pdf":"http://arxiv.org/pdf/1804.03641v2.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":"audio-visual-scene-analysis-with-self","repo_url":"https://github.com/andrewowens/multisensory","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"audio-source-separation","task_name":"Audio Source Separation"},{"task_slug":"sound-source-localization","task_name":"Sound Source Localization"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.03641","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}