{"id":"https://openalex.org/W4283382486","doi":"https://doi.org/10.1145/3512527.3531364","title":"Self-Lifting: A Novel Framework for Unsupervised Voice-Face Association Learning","display_name":"Self-Lifting: A Novel Framework for Unsupervised Voice-Face Association Learning","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283382486","doi":"https://doi.org/10.1145/3512527.3531364"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100654878","display_name":"Guangyu Chen","orcid":"https://orcid.org/0000-0002-0932-6563"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Chen","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052015929","display_name":"Deyuan Zhang","orcid":"https://orcid.org/0000-0002-4731-7211"},"institutions":[{"id":"https://openalex.org/I125904092","display_name":"Shenyang Aerospace University","ror":"https://ror.org/02423gm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I125904092"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyuan Zhang","raw_affiliation_strings":["Shenyang Aerospace University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenyang Aerospace University, Beijing, China","institution_ids":["https://openalex.org/I125904092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603187","display_name":"Tao Liu","orcid":"https://orcid.org/0000-0002-9303-9400"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Liu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008721449","display_name":"Xiaoyong Du","orcid":"https://orcid.org/0000-0002-5757-9135"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyong Du","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0303,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88956127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"527","last_page":"535"},"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/T11448","display_name":"Face recognition and analysis","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.8072178363800049},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.8044489622116089},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6693652272224426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6687192916870117},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.5885455012321472},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5809894800186157},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.535163164138794},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4953269064426422},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48612403869628906},{"id":"https://openalex.org/keywords/competitive-learning","display_name":"Competitive learning","score":0.47862452268600464},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.47156426310539246},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.44676411151885986},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4420424997806549},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4192601442337036},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4161650836467743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4119245409965515},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20728805661201477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072178363800049},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.8044489622116089},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6693652272224426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6687192916870117},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.5885455012321472},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5809894800186157},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.535163164138794},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4953269064426422},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48612403869628906},{"id":"https://openalex.org/C120822770","wikidata":"https://www.wikidata.org/wiki/Q5156355","display_name":"Competitive learning","level":3,"score":0.47862452268600464},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47156426310539246},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.44676411151885986},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4420424997806549},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4192601442337036},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4161650836467743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4119245409965515},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20728805661201477},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512527.3531364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4518451911","display_name":null,"funder_award_id":"U1711262,61472428","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1977556410","https://openalex.org/W2032001302","https://openalex.org/W2077881910","https://openalex.org/W2097117768","https://openalex.org/W2127211243","https://openalex.org/W2138621090","https://openalex.org/W2726515241","https://openalex.org/W2883725317","https://openalex.org/W2897663715","https://openalex.org/W2945210081","https://openalex.org/W2962918445","https://openalex.org/W2963350250","https://openalex.org/W2963801643","https://openalex.org/W2964271799","https://openalex.org/W2967957126","https://openalex.org/W2997819898","https://openalex.org/W3008625353","https://openalex.org/W3024869864","https://openalex.org/W3034725201","https://openalex.org/W3171007011","https://openalex.org/W3177326298","https://openalex.org/W4255556797","https://openalex.org/W4289665794"],"related_works":["https://openalex.org/W3148060700","https://openalex.org/W2096837800","https://openalex.org/W2749300598","https://openalex.org/W3174759195","https://openalex.org/W2794908468","https://openalex.org/W2531570999","https://openalex.org/W4287121366","https://openalex.org/W3167013339","https://openalex.org/W2553312496","https://openalex.org/W2163389298"],"abstract_inverted_index":{"Voice-face":[0],"association":[1],"learning":[2,42,108],"(VFAL)":[3],"aims":[4],"to":[5,87,90,104,121],"tap":[6],"into":[7,74],"the":[8,28,66,75,94,97,106,112,123,140,149,158],"potential":[9],"connections":[10],"between":[11],"voices":[12],"and":[13,62,152],"faces.":[14],"Most":[15],"studies":[16],"currently":[17],"address":[18],"this":[19,36],"problem":[20],"in":[21],"a":[22,79],"supervised":[23,159],"manner,":[24],"which":[25,46,110],"cannot":[26],"exploit":[27],"wealth":[29],"of":[30,60],"unlabeled":[31,49,69,134],"video":[32,50,70,135],"data.":[33],"To":[34],"solve":[35],"problem,":[37],"we":[38],"propose":[39],"an":[40],"unsupervised":[41,83,150],"framework:":[43],"Self-Lifting":[44],"(SL),":[45],"can":[47,131],"use":[48,133],"data":[51,71,136],"for":[52,137],"learning.":[53,138],"This":[54],"framework":[55,130],"includes":[56],"two":[57,116],"iterative":[58],"steps":[59,117],"\"clustering\"":[61],"\"metric":[63],"learning\".":[64],"In":[65,93],"first":[67],"step,":[68,96],"is":[72,85,99,163],"mapped":[73],"feature":[76],"space":[77],"by":[78],"coarse":[80],"model.":[81,114],"Then":[82],"clustering":[84],"leveraged":[86],"allocate":[88],"pseudo-label":[89,98],"each":[91],"video.":[92],"second":[95],"used":[100],"as":[101],"supervisory":[102],"information":[103],"guide":[105],"metric":[107],"process,":[109],"produces":[111],"refined":[113],"These":[115],"are":[118],"performed":[119],"alternately":[120],"lift":[122],"model's":[124],"performance.":[125],"Experiments":[126],"show":[127],"that":[128],"our":[129,143],"effectively":[132],"On":[139],"VoxCeleb":[141],"dataset,":[142],"approach":[144],"achieves":[145],"SOTA":[146],"results":[147],"among":[148],"methods":[151],"has":[153],"competitive":[154],"performance":[155],"compared":[156],"with":[157],"competitors.":[160],"Our":[161],"code":[162],"released":[164],"on":[165],"Github.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}