{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/1804.03641","atlas_url":"https://app.syntology.ai/?focus=1804.03641","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1804.03641"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1804.03641\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1804.03641"},"call":"get_concepts_for_paper(arxiv_id=\"1804.03641\")"}],"by_repo":[{"repo":"andrewowens/multisensory","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"96dbe08e954e95ea48718c8b3d4f5c9ca38afa154e8fc7235cf93c41b822ce29","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}