{"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/learning-to-separate-object-sounds-by","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","arxiv_id":"1804.01665","date":"2018-04-05","proceeding":"ECCV 2018 9","authors":["Ruohan Gao","Rogerio Feris","Kristen Grauman"],"abstract":"Perceiving a scene most fully requires all the senses. Yet modeling how\nobjects look and sound is challenging: most natural scenes and events contain\nmultiple objects, and the audio track mixes all the sound sources together. We\npropose to learn audio-visual object models from unlabeled video, then exploit\nthe visual context to perform audio source separation in novel videos. Our\napproach relies on a deep multi-instance multi-label learning framework to\ndisentangle the audio frequency bases that map to individual visual objects,\neven without observing/hearing those objects in isolation. We show how the\nrecovered disentangled bases can be used to guide audio source separation to\nobtain better-separated, object-level sounds. Our work is the first to learn\naudio source separation from large-scale \"in the wild\" videos containing\nmultiple audio sources per video. We obtain state-of-the-art results on\nvisually-aided audio source separation and audio denoising. Our video results:\nhttp://vision.cs.utexas.edu/projects/separating_object_sounds/","url_abs":"http://arxiv.org/abs/1804.01665v2","url_pdf":"http://arxiv.org/pdf/1804.01665v2.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":"learning-to-separate-object-sounds-by","repo_url":"https://github.com/rhgao/Deep-MIML-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-separate-object-sounds-by","repo_url":"https://github.com/rhgao/separating-object-sounds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"audio-denoising","task_name":"Audio Denoising"},{"task_slug":"audio-source-separation","task_name":"Audio Source Separation"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"multi-label-learning","task_name":"Multi-Label Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.01665","atlas_url":"https://app.syntology.ai/?focus=1804.01665","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}