{"id":"https://openalex.org/W3049356352","doi":"https://doi.org/10.1145/3380549","title":"Listen, Look, and Find the One","display_name":"Listen, Look, and Find the One","publication_year":2020,"publication_date":"2020-05-22","ids":{"openalex":"https://openalex.org/W3049356352","doi":"https://doi.org/10.1145/3380549","mag":"3049356352"},"language":"en","primary_location":{"id":"doi:10.1145/3380549","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3380549","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100411506","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0003-0770-9891"},"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"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]},{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["AI Research of JD.com","NERCMS, School of Computer Sicence, Wuhan University"],"raw_orcid":"https://orcid.org/0000-0003-0770-9891","affiliations":[{"raw_affiliation_string":"AI Research of JD.com","institution_ids":["https://openalex.org/I4210103986","https://openalex.org/I72427458"]},{"raw_affiliation_string":"NERCMS, School of Computer Sicence, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068917997","display_name":"Wu Liu","orcid":"https://orcid.org/0000-0003-1633-7575"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]},{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wu Liu","raw_affiliation_strings":["AI Research of JD.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research of JD.com","institution_ids":["https://openalex.org/I4210103986","https://openalex.org/I72427458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450249","display_name":"Jun Chen","orcid":"https://orcid.org/0000-0003-1376-0167"},"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":"Jun Chen","raw_affiliation_strings":["NERCMS, School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERCMS, School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410391","display_name":"Xiaobo Wang","orcid":"https://orcid.org/0000-0002-6815-2751"},"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"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]},{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiaobo Wang","raw_affiliation_strings":["AI Research of JD.com","NERCMS, School of Computer Sicence, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research of JD.com","institution_ids":["https://openalex.org/I4210103986","https://openalex.org/I72427458"]},{"raw_affiliation_string":"NERCMS, School of Computer Sicence, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054311881","display_name":"Chenggang Yan","orcid":"https://orcid.org/0000-0003-1204-0512"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenggang Yan","raw_affiliation_strings":["Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]},{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["AI Research of JD.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research of JD.com","institution_ids":["https://openalex.org/I4210103986","https://openalex.org/I72427458"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2501,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.79872904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"16","issue":"2","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9972000122070312,"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/multimodality","display_name":"Multimodality","score":0.7869139909744263},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7831680178642273},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.7050114870071411},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6723052263259888},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6128992438316345},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5913439393043518},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5290650129318237},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5210587382316589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5178185105323792},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4815852642059326},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47543027997016907},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4263572692871094},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.4148942232131958},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.4142005443572998},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13062530755996704},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11308786273002625},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09792014956474304}],"concepts":[{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.7869139909744263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831680178642273},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.7050114870071411},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6723052263259888},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6128992438316345},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5913439393043518},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5290650129318237},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5210587382316589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5178185105323792},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4815852642059326},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47543027997016907},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4263572692871094},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.4148942232131958},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.4142005443572998},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13062530755996704},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11308786273002625},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09792014956474304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3380549","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3380549","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3332149071","display_name":null,"funder_award_id":"61876135, 61801335 and U1611461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5973182375","display_name":null,"funder_award_id":"2018AAA062","funder_id":"https://openalex.org/F4320335792","funder_display_name":"Hubei Technological Innovation Special Fund"},{"id":"https://openalex.org/G6063697507","display_name":null,"funder_award_id":"2019XD-A12","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320335792","display_name":"Hubei Technological Innovation Special Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1995884877","https://openalex.org/W2019370496","https://openalex.org/W2070862184","https://openalex.org/W2117539524","https://openalex.org/W2341528187","https://openalex.org/W2499468060","https://openalex.org/W2520742745","https://openalex.org/W2527629189","https://openalex.org/W2570915410","https://openalex.org/W2572045081","https://openalex.org/W2580365077","https://openalex.org/W2619697695","https://openalex.org/W2726515241","https://openalex.org/W2761121566","https://openalex.org/W2783367051","https://openalex.org/W2786437919","https://openalex.org/W2808631503","https://openalex.org/W2888003147","https://openalex.org/W2900619470","https://openalex.org/W2916994131","https://openalex.org/W2940928832","https://openalex.org/W2943826729","https://openalex.org/W2964307722","https://openalex.org/W2966042949","https://openalex.org/W3099193058","https://openalex.org/W3101998545"],"related_works":["https://openalex.org/W2997512100","https://openalex.org/W1485630101","https://openalex.org/W2355180337","https://openalex.org/W2331043530","https://openalex.org/W2498017833","https://openalex.org/W2393933887","https://openalex.org/W112744582","https://openalex.org/W2044053147","https://openalex.org/W2358583730","https://openalex.org/W2378623121"],"abstract_inverted_index":{"Person":[0],"search":[1,8,80,178,221],"with":[2,81,191],"one":[3,15],"portrait,":[4],"which":[5,33,130],"attempts":[6],"to":[7,66,96,115,174,204,210],"the":[9,28,37,50,88,98,110,132,140,148,152,156,166,170,186,214,217,224],"targets":[10,162],"in":[11,27,49,59,69,155,189],"arbitrary":[12],"scenes":[13],"using":[14,127],"portrait":[16],"image":[17],"at":[18],"a":[19,144,195],"time,":[20],"is":[21,94],"an":[22,74,91,117],"essential":[23],"yet":[24],"unexplored":[25],"problem":[26],"multimedia":[29],"field.":[30],"Existing":[31],"approaches,":[32],"predominantly":[34],"depend":[35],"on":[36,165,213],"visual":[38],"information":[39],"of":[40,112,169],"persons,":[41],"cannot":[42],"solve":[43],"problems":[44],"when":[45],"there":[46],"are":[47],"variations":[48],"person\u2019s":[51],"appearance":[52,142],"caused":[53],"by":[54,126],"complex":[55],"environments":[56],"and":[57,62,84,103,134,139,180],"changes":[58],"pose,":[60],"makeup,":[61],"clothing.":[63],"In":[64,87,147],"contrast":[65],"existing":[67],"methods,":[68],"this":[70],"article,":[71],"we":[72,158,184],"propose":[73],"associative":[75,92],"multimodality":[76,121,153,177,219],"index":[77,122],"for":[78],"person":[79,220],"face,":[82,101],"body,":[83,102],"voice":[85,104,135],"information.":[86,105],"offline":[89],"stage,":[90,150],"network":[93],"proposed":[95,218],"learn":[97],"relationships":[99],"among":[100],"It":[106],"can":[107,123,159],"adaptively":[108],"estimate":[109],"weights":[111],"each":[113],"embedding":[114],"construct":[116,185],"appropriate":[118],"representation.":[119],"The":[120],"be":[124],"built":[125],"these":[128],"representations,":[129],"exploit":[131],"face":[133],"as":[136,143],"long-term":[137],"keys":[138],"body":[141],"short-term":[145],"connection.":[146],"online":[149],"through":[151],"association":[154],"index,":[157],"retrieve":[160],"all":[161],"depending":[163],"only":[164],"facial":[167],"features":[168],"query":[171],"portrait.":[172],"Furthermore,":[173],"evaluate":[175],"our":[176],"framework":[179,222],"facilitate":[181],"related":[182],"research,":[183],"Cast":[187],"Search":[188],"Movies":[190],"Voice":[192],"(CSM-V)":[193],"dataset,":[194,216],"large-scale":[196],"benchmark":[197],"that":[198],"contains":[199],"127K":[200],"annotated":[201],"voices":[202],"corresponding":[203],"tracklets":[205],"from":[206],"192":[207],"movies.":[208],"According":[209],"extensive":[211],"experiments":[212],"CSM-V":[215],"outperforms":[223],"state-of-the-art":[225],"methods.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}