{"id":"https://openalex.org/W2936229313","doi":"https://doi.org/10.1109/icassp.2019.8682467","title":"Self-supervised Audio-visual Co-segmentation","display_name":"Self-supervised Audio-visual Co-segmentation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936229313","doi":"https://doi.org/10.1109/icassp.2019.8682467","mag":"2936229313"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.09013","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010091252","display_name":"Andrew Rouditchenko","orcid":"https://orcid.org/0000-0002-0063-3612"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["RU","US"],"is_corresponding":false,"raw_author_name":"Andrew Rouditchenko","raw_affiliation_strings":["MIT","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101826600","display_name":"Hang Zhao","orcid":"https://orcid.org/0009-0002-8690-415X"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["RU","US"],"is_corresponding":false,"raw_author_name":"Hang Zhao","raw_affiliation_strings":["MIT","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuang Gan","raw_affiliation_strings":["MIT-IBM Watson AI Lab","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110628266","display_name":"Josh H. McDermott","orcid":"https://orcid.org/0000-0002-3965-2503"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["RU","US"],"is_corresponding":false,"raw_author_name":"Josh McDermott","raw_affiliation_strings":["MIT","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085020955","display_name":"Antonio Torralba","orcid":"https://orcid.org/0000-0003-4915-0256"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Antonio Torralba","raw_affiliation_strings":["MIT","-MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]},{"raw_affiliation_string":"-MIT","institution_ids":["https://openalex.org/I4210109586"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7218,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84312476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2357","last_page":"2361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8169964551925659},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7574629783630371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6832556128501892},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5926647186279297},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5374560356140137},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5351930856704712},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5080676078796387},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4509810209274292},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4371487498283386},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.43678462505340576},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.434267520904541},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4106703996658325},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09298437833786011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169964551925659},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7574629783630371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6832556128501892},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5926647186279297},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5374560356140137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5351930856704712},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5080676078796387},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4509810209274292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4371487498283386},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.43678462505340576},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.434267520904541},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4106703996658325},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09298437833786011},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp.2019.8682467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.09013","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.09013","pdf_url":"https://arxiv.org/pdf/1904.09013","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/138075","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/138075","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"Article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/138075.2","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/138075.2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"doi:10.48550/arxiv.1904.09013","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.09013","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2936229313","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.09013","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.09013","pdf_url":"https://arxiv.org/pdf/1904.09013","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5099999904632568,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2936229313.pdf","grobid_xml":"https://content.openalex.org/works/W2936229313.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1964538581","https://openalex.org/W1971168548","https://openalex.org/W2058670155","https://openalex.org/W2127851351","https://openalex.org/W2150415460","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2222512263","https://openalex.org/W2295107390","https://openalex.org/W2315268655","https://openalex.org/W2511428026","https://openalex.org/W2547875792","https://openalex.org/W2586148577","https://openalex.org/W2619697695","https://openalex.org/W2660943524","https://openalex.org/W2737258237","https://openalex.org/W2753738274","https://openalex.org/W2796992393","https://openalex.org/W2950133079","https://openalex.org/W2962732076","https://openalex.org/W2962756039","https://openalex.org/W2962865004","https://openalex.org/W2963680395","https://openalex.org/W2963902314","https://openalex.org/W2964109005","https://openalex.org/W6639824700","https://openalex.org/W6714030504","https://openalex.org/W6725104640","https://openalex.org/W6729448088","https://openalex.org/W6729831399","https://openalex.org/W6744627333","https://openalex.org/W6749336676","https://openalex.org/W6749633790","https://openalex.org/W6750169759","https://openalex.org/W6750591037","https://openalex.org/W6750599028","https://openalex.org/W6750651883"],"related_works":["https://openalex.org/W2962699416","https://openalex.org/W2939726645","https://openalex.org/W3046031607","https://openalex.org/W3105043467","https://openalex.org/W3163880376","https://openalex.org/W2889567228","https://openalex.org/W2901412525","https://openalex.org/W2917696722","https://openalex.org/W3017327777","https://openalex.org/W83181605","https://openalex.org/W2758665125","https://openalex.org/W2755686789","https://openalex.org/W2801031914","https://openalex.org/W3161531798","https://openalex.org/W2964048159","https://openalex.org/W2962960500","https://openalex.org/W2619697695","https://openalex.org/W3007167099","https://openalex.org/W3005203926","https://openalex.org/W3117190228"],"abstract_inverted_index":{"Segmenting":[0],"objects":[1],"in":[2,8,13,73,109],"images":[3],"and":[4,37,77,90,112],"separating":[5],"sound":[6,38,91,113],"sources":[7],"audio":[9],"are":[10],"challenging":[11],"tasks,":[12],"part":[14],"because":[15],"traditional":[16],"approaches":[17],"require":[18],"large":[19],"amounts":[20],"of":[21,53],"labeled":[22],"data.":[23],"In":[24],"this":[25],"paper":[26],"we":[27,65],"develop":[28],"a":[29,67],"neural":[30,75],"network":[31,82],"model":[32,49,105],"for":[33],"visual":[34],"object":[35],"segmentation":[36,89,111],"source":[39,92,114],"separation":[40,93],"that":[41,57,102],"learns":[42],"from":[43],"natural":[44],"videos":[45],"through":[46],"self-supervision.":[47],"The":[48],"is":[50],"an":[51],"extension":[52],"recently":[54],"proposed":[55],"work":[56],"maps":[58],"image":[59,88],"pixels":[60],"to":[61,70,81,85],"sounds":[62],"[1].":[63],"Here,":[64],"introduce":[66],"learning":[68],"approach":[69],"disentangle":[71],"concepts":[72],"the":[74,103],"networks,":[76],"assign":[78],"semantic":[79,110],"categories":[80],"feature":[83],"channels":[84],"enable":[86],"independent":[87],"after":[94],"audio-visual":[95],"training":[96],"on":[97],"videos.":[98],"Our":[99],"evaluations":[100],"show":[101],"disentangled":[104],"outperforms":[106],"several":[107],"baselines":[108],"separation.":[115]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}