{"id":"https://openalex.org/W3217354204","doi":"https://doi.org/10.1145/3503161.3548027","title":"AVA-AVD: Audio-visual Speaker Diarization in the Wild","display_name":"AVA-AVD: Audio-visual Speaker Diarization in the Wild","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W3217354204","doi":"https://doi.org/10.1145/3503161.3548027","mag":"3217354204"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548027","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548027","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548027","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548027","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028544628","display_name":"Zhongcong Xu","orcid":"https://orcid.org/0000-0003-3511-8466"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eric Zhongcong Xu","raw_affiliation_strings":["Showlab, National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Showlab, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072108662","display_name":"Zeyang Song","orcid":"https://orcid.org/0000-0003-0122-8704"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zeyang Song","raw_affiliation_strings":["Showlab, National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Showlab, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Satoshi Tsutsui","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Satoshi Tsutsui","raw_affiliation_strings":["Showlab, National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Showlab, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057659098","display_name":"Chao Feng","orcid":"https://orcid.org/0000-0001-5440-9758"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chao Feng","raw_affiliation_strings":["Showlab, National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Showlab, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008999954","display_name":"Mang Ye","orcid":"https://orcid.org/0000-0003-3989-7655"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mang Ye","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mike Zheng Shou","raw_affiliation_strings":["Showlab, National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Showlab, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3838","last_page":"3847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.882774829864502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7956140041351318},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7065409421920776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5862010717391968},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5322306752204895},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5225255489349365},{"id":"https://openalex.org/keywords/visibility","display_name":"Visibility","score":0.4238576292991638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3799886703491211},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2504241168498993}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.882774829864502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956140041351318},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7065409421920776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5862010717391968},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5322306752204895},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5225255489349365},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.4238576292991638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3799886703491211},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2504241168498993},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3503161.3548027","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548027","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548027","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.14448","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.14448","pdf_url":"https://arxiv.org/pdf/2111.14448","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"},{"id":"mag:3217354204","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2111.14448","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2111.14448","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2111.14448","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/3503161.3548027","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548027","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548027","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3217354204.pdf","grobid_xml":"https://content.openalex.org/works/W3217354204.grobid-xml"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W1800068500","https://openalex.org/W1929856797","https://openalex.org/W1955055330","https://openalex.org/W1971791733","https://openalex.org/W1971901154","https://openalex.org/W2025341678","https://openalex.org/W2035890032","https://openalex.org/W2088692057","https://openalex.org/W2125336414","https://openalex.org/W2127211243","https://openalex.org/W2150769028","https://openalex.org/W2164899449","https://openalex.org/W2165874743","https://openalex.org/W2194775991","https://openalex.org/W2236062296","https://openalex.org/W2316138215","https://openalex.org/W2325939864","https://openalex.org/W2394699868","https://openalex.org/W2515770085","https://openalex.org/W2593814746","https://openalex.org/W2601450892","https://openalex.org/W2604379605","https://openalex.org/W2619697695","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2950864153","https://openalex.org/W2950870964","https://openalex.org/W2951237705","https://openalex.org/W2962698660","https://openalex.org/W2962788625","https://openalex.org/W2963307811","https://openalex.org/W2963470929","https://openalex.org/W2963801643","https://openalex.org/W2963839617","https://openalex.org/W2963887950","https://openalex.org/W2963907629","https://openalex.org/W2964048159","https://openalex.org/W2964080601","https://openalex.org/W2964105864","https://openalex.org/W2964283370","https://openalex.org/W2969985801","https://openalex.org/W2970458417","https://openalex.org/W2972449503","https://openalex.org/W2972729214","https://openalex.org/W2982672255","https://openalex.org/W2987802279","https://openalex.org/W3013020904","https://openalex.org/W3015463733","https://openalex.org/W3016031604","https://openalex.org/W3016098309","https://openalex.org/W3025260599","https://openalex.org/W3034552680","https://openalex.org/W3038871978","https://openalex.org/W3091905774","https://openalex.org/W3095212884","https://openalex.org/W3096609285","https://openalex.org/W3096861448","https://openalex.org/W3097741049","https://openalex.org/W3103165805","https://openalex.org/W3108614371","https://openalex.org/W3126757411","https://openalex.org/W3162347631","https://openalex.org/W3162899647","https://openalex.org/W3163527109","https://openalex.org/W3168654180","https://openalex.org/W3172752666","https://openalex.org/W3177326298","https://openalex.org/W3178462146","https://openalex.org/W3182657421","https://openalex.org/W3183689464","https://openalex.org/W3203209821","https://openalex.org/W3205786327","https://openalex.org/W3206008172","https://openalex.org/W6678809451"],"related_works":[],"abstract_inverted_index":{"Audio-visual":[0],"speaker":[1],"diarization":[2,17,50,77],"aims":[3],"at":[4,168],"detecting":[5],"\"who":[6],"spoke":[7],"when''":[8],"using":[9],"both":[10],"auditory":[11],"and":[12,45,102,161],"visual":[13],"signals.":[14],"Existing":[15],"audio-visual":[16],"datasets":[18],"are":[19,32],"mainly":[20],"focused":[21],"on":[22,134],"indoor":[23],"environments":[24],"like":[25],"meeting":[26],"rooms":[27],"or":[28],"news":[29],"studios,":[30],"which":[31,121],"quite":[33],"different":[34],"from":[35],"in-the-wild":[36,80],"videos":[37,81],"in":[38],"many":[39],"scenarios":[40],"such":[41],"as":[42,152],"movies,":[43],"documentaries,":[44],"audience":[46],"sitcoms.":[47],"To":[48],"develop":[49],"methods":[51,147],"for":[52,79],"these":[53],"challenging":[54,93],"videos,":[55],"we":[56,114],"create":[57],"the":[58,84,96,112,116,154],"AVA":[59],"Audio-Visual":[60,117],"Diarization":[61],"(AVA-AVD)":[62],"dataset.":[63],"Our":[64,159],"experiments":[65],"demonstrate":[66],"that":[67,83,139],"adding":[68],"AVA-AVD":[69],"into":[70],"training":[71],"set":[72],"can":[73,144],"produce":[74],"significantly":[75],"better":[76],"models":[78],"despite":[82],"data":[85,160],"is":[86,92,149],"relatively":[87],"small.":[88],"Moreover,":[89],"this":[90],"benchmark":[91],"due":[94],"to":[95,129],"diverse":[97],"scenes,":[98],"complicated":[99],"acoustic":[100],"conditions,":[101],"completely":[103],"off-screen":[104,157],"speakers.":[105,158],"As":[106],"a":[107,123],"first":[108],"step":[109],"towards":[110],"addressing":[111],"challenges,":[113],"design":[115],"Relation":[118],"Network":[119],"(AVR-Net)":[120],"introduces":[122],"simple":[124],"yet":[125],"effective":[126],"modality":[127],"mask":[128],"capture":[130],"discriminative":[131],"information":[132],"based":[133],"face":[135],"visibility.":[136],"Experiments":[137],"show":[138],"our":[140],"method":[141],"not":[142],"only":[143],"outperform":[145],"state-of-the-art":[146],"but":[148],"more":[150],"robust":[151],"varying":[153],"ratio":[155],"of":[156],"code":[162],"has":[163],"been":[164],"made":[165],"publicly":[166],"available":[167],"\\textcolormagenta":[169],"\\urlhttps://github.com/showlab/AVA-AVD":[170],".":[171]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-12-06T00:00:00"}