{"id":"https://openalex.org/W3048939150","doi":"https://doi.org/10.1145/3394171.3413869","title":"Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning","display_name":"Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3048939150","doi":"https://doi.org/10.1145/3394171.3413869","mag":"3048939150"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.05789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ying Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Cheng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruize Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruize Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhihao Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Pan","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Feng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yuejie Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuejie Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":91,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3884","last_page":"3892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7918999791145325},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5468999743461609},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5453000068664551},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.522599995136261},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.49549999833106995},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4494999945163727},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4260999858379364},{"id":"https://openalex.org/keywords/pretext","display_name":"Pretext","score":0.40790000557899475},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39169999957084656},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.38769999146461487}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7918999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523999810218811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.58160001039505},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46050000190734863},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4494999945163727},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4154999852180481},{"id":"https://openalex.org/C2779627259","wikidata":"https://www.wikidata.org/wiki/Q779763","display_name":"Pretext","level":3,"score":0.40790000557899475},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.3456000089645386},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33570000529289246},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3231000006198883},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.31929999589920044},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.301800012588501},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394171.3413869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.05789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.05789","pdf_url":"https://arxiv.org/pdf/2008.05789","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.05789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.05789","pdf_url":"https://arxiv.org/pdf/2008.05789","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W413992410","https://openalex.org/W1483019628","https://openalex.org/W1522734439","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2038485832","https://openalex.org/W2065274193","https://openalex.org/W2066132206","https://openalex.org/W2105582566","https://openalex.org/W2154642173","https://openalex.org/W2171819471","https://openalex.org/W2194775991","https://openalex.org/W2235381883","https://openalex.org/W2295107390","https://openalex.org/W2326735091","https://openalex.org/W2511428026","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2883429621","https://openalex.org/W2886564777","https://openalex.org/W2950864153","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2982619606","https://openalex.org/W3015734344"],"related_works":[],"abstract_inverted_index":{"When":[0],"watching":[1],"videos,":[2],"the":[3,17,22,52,79,101,105,118,132,141,176],"occurrence":[4],"of":[5,19,24,55,136],"a":[6,47,63],"visual":[7,35,97],"event":[8],"is":[9,28],"often":[10],"accompanied":[11],"by":[12,50],"an":[13,29],"audio":[14,33],"event,":[15],"e.g.,":[16],"voice":[18],"lip":[20],"motion,":[21],"music":[23],"playing":[25],"instruments.":[26],"There":[27],"underlying":[30],"correlation":[31],"between":[32,107],"and":[34,81,103,134,152,168],"events,":[36],"which":[37,179],"can":[38,174],"be":[39],"utilized":[40],"as":[41],"free":[42],"supervised":[43],"information":[44],"to":[45,70,93,100],"train":[46],"neural":[48],"network":[49],"solving":[51],"pretext":[53,119],"task":[54,120],"audio-visual":[56],"synchronization.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,87,139],"propose":[62],"novel":[64],"self-supervised":[65,166],"framework":[66],"with":[67,126,164],"co-attention":[68,91],"mechanism":[69],"learn":[71],"generic":[72],"cross-modal":[73],"representations":[74],"from":[75],"unlabelled":[76],"videos":[77],"in":[78],"wild,":[80],"further":[82,130],"benefit":[83],"downstream":[84,146],"tasks.":[85],"Specifically,":[86],"explore":[88],"three":[89],"different":[90],"modules":[92],"focus":[94],"on":[95,117,144],"discriminative":[96],"regions":[98],"correlated":[99],"sounds":[102],"introduce":[104],"interactions":[106],"them.":[108],"Experiments":[109],"show":[110],"that":[111,158,171],"our":[112,137,159,172],"model":[113,143,160],"achieves":[114],"state-of-the-art":[115],"performance":[116],"while":[121],"having":[122],"fewer":[123],"parameters":[124],"compared":[125],"existing":[127],"methods.":[128],"To":[129],"evaluate":[131],"generalizability":[133],"transferability":[135],"approach,":[138],"apply":[140],"pre-trained":[142],"two":[145],"tasks,":[147],"i.e.,":[148],"sound":[149,182],"source":[150],"localization":[151],"action":[153],"recognition.":[154],"Extensive":[155],"experiments":[156],"demonstrate":[157],"provides":[161],"competitive":[162],"results":[163],"other":[165],"methods,":[167],"also":[169],"indicate":[170],"approach":[173],"tackle":[175],"challenging":[177],"scenes":[178],"contain":[180],"multiple":[181],"sources.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-08-18T00:00:00"}