{"id":"https://openalex.org/W4285603046","doi":"https://doi.org/10.24963/ijcai.2022/526","title":"Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast","display_name":"Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285603046","doi":"https://doi.org/10.24963/ijcai.2022/526"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/526","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/526","pdf_url":"https://www.ijcai.org/proceedings/2022/0526.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0526.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018669598","display_name":"Boqing Zhu","orcid":"https://orcid.org/0000-0001-7867-2112"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boqing Zhu","raw_affiliation_strings":["National University of Defense Technology","College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kele Xu","raw_affiliation_strings":["National University of Defense Technology","College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102003608","display_name":"Changjian Wang","orcid":"https://orcid.org/0000-0002-1160-0365"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjian Wang","raw_affiliation_strings":["National University Of Defense Technology","College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University Of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678400","display_name":"Zheng Qin","orcid":"https://orcid.org/0000-0001-5645-5088"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Qin","raw_affiliation_strings":["National University of Defense Technology","College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101652545","display_name":"Tao Sun","orcid":"https://orcid.org/0000-0002-8967-8760"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Sun","raw_affiliation_strings":["National University of Defense Technology","College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076087924","display_name":"Huaimin Wang","orcid":"https://orcid.org/0000-0003-0376-640X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaimin Wang","raw_affiliation_strings":["National University of Defense Technology","College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101645557","display_name":"Yuxing Peng","orcid":"https://orcid.org/0000-0002-8223-5588"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxing Peng","raw_affiliation_strings":["National University of Defense Technology","College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5013340793"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":2.7037,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.92543444,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3787","last_page":"3794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9821000099182129,"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/computer-science","display_name":"Computer science","score":0.7693052291870117},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6739746332168579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6057994961738586},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5537227988243103},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5000596046447754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4749888479709625},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.419586181640625},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3723692297935486},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3476647138595581},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33467820286750793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7693052291870117},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6739746332168579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6057994961738586},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5537227988243103},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5000596046447754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4749888479709625},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.419586181640625},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3723692297935486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3476647138595581},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33467820286750793},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/526","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/526","pdf_url":"https://www.ijcai.org/proceedings/2022/0526.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/526","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/526","pdf_url":"https://www.ijcai.org/proceedings/2022/0526.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5600000023841858,"display_name":"Reduced inequalities"},{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285603046.pdf","grobid_xml":"https://content.openalex.org/works/W4285603046.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2077171211","https://openalex.org/W2163899439","https://openalex.org/W2194775991","https://openalex.org/W2726515241","https://openalex.org/W2897663715","https://openalex.org/W2950180292","https://openalex.org/W2951237705","https://openalex.org/W2962918445","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2970903655","https://openalex.org/W2990408345","https://openalex.org/W3005680577","https://openalex.org/W3010094231","https://openalex.org/W3020430839","https://openalex.org/W3022061250","https://openalex.org/W3024147341","https://openalex.org/W3034576826","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3037309139","https://openalex.org/W3090114175","https://openalex.org/W3090114880","https://openalex.org/W3102363610","https://openalex.org/W3115964123","https://openalex.org/W3175300676","https://openalex.org/W3176780013","https://openalex.org/W3177326298","https://openalex.org/W3184648662","https://openalex.org/W3188030217","https://openalex.org/W3190580390","https://openalex.org/W4287812705","https://openalex.org/W4297808394"],"related_works":["https://openalex.org/W1557094818","https://openalex.org/W2183246718","https://openalex.org/W2099261052","https://openalex.org/W3209204065","https://openalex.org/W1755711892","https://openalex.org/W2069592018","https://openalex.org/W2160907113","https://openalex.org/W2075740387","https://openalex.org/W2070813941","https://openalex.org/W2105707930"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"approach":[3,166],"to":[4,24,81,158,191],"learn":[5,121],"voice-face":[6,173],"representations":[7],"from":[8,146],"the":[9,26,35,48,55,85,94,122,136,141,154,164,179],"talking":[10],"face":[11],"videos,":[12,40],"without":[13],"any":[14],"identity":[15],"labels.":[16],"Previous":[17],"works":[18],"employ":[19],"cross-modal":[20,95,144,149],"instance":[21],"discrimination":[22],"tasks":[23],"establish":[25],"correlation":[27,57,66],"of":[28,38,76,103,110,143,148],"voice":[29],"and":[30,61,106,113],"face.":[31],"These":[32],"methods":[33,105,170],"neglect":[34],"semantic":[36],"content":[37],"different":[39,133],"introducing":[41],"false-negative":[42],"pairs":[43,50],"as":[44],"training":[45],"noise.":[46],"Furthermore,":[47],"positive":[49],"are":[51],"constructed":[52],"based":[53],"on":[54,171],"natural":[56],"between":[58],"audio":[59],"clips":[60],"visual":[62],"frames.":[63],"However,":[64],"this":[65],"might":[67],"be":[68],"weak":[69],"or":[70],"inaccurate":[71],"in":[72,132,178],"a":[73,187],"large":[74],"amount":[75],"real-world":[77],"data,":[78],"which":[79,100],"leads":[80],"deviating":[82],"positives":[83,128],"into":[84],"contrastive":[86,97,104,194],"paradigm.":[87],"To":[88],"address":[89],"these":[90],"issues,":[91],"we":[92,151],"propose":[93],"prototype":[96],"learning":[98],"(CMPC),":[99],"takes":[101],"advantage":[102],"resists":[107],"adverse":[108],"effects":[109],"false":[111],"negatives":[112],"deviate":[114],"positives.":[115],"On":[116,135],"one":[117],"hand,":[118,138],"CMPC":[119],"could":[120],"intra-class":[123],"invariance":[124],"by":[125,139],"constructing":[126],"semantic-wise":[127],"via":[129],"unsupervised":[130,169],"clustering":[131],"modalities.":[134],"other":[137],"comparing":[140],"similarities":[142],"instances":[145],"that":[147,163],"prototypes,":[150],"dynamically":[152],"recalibrate":[153],"unlearnable":[155],"instances'":[156],"contribution":[157],"overall":[159],"loss.":[160],"Experiments":[161],"show":[162],"proposed":[165],"outperforms":[167],"state-of-the-art":[168],"various":[172],"association":[174],"evaluation":[175],"protocols.":[176],"Additionally,":[177],"low-shot":[180],"supervision":[181],"setting,":[182],"our":[183],"method":[184],"also":[185],"has":[186],"significant":[188],"improvement":[189],"compared":[190],"previous":[192],"instance-wise":[193],"learning.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}