{"id":"https://openalex.org/W4387969939","doi":"https://doi.org/10.1145/3581783.3611938","title":"Taking a Part for the Whole: An Archetype-agnostic Framework for Voice-Face Association","display_name":"Taking a Part for the Whole: An Archetype-agnostic Framework for Voice-Face Association","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969939","doi":"https://doi.org/10.1145/3581783.3611938"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611938","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5015121859","display_name":"G T Chen","orcid":"https://orcid.org/0009-0001-3468-9913"},"institutions":[{"id":"https://openalex.org/I119045251","display_name":"Huaqiao University","ror":"https://ror.org/03frdh605","country_code":"CN","type":"education","lineage":["https://openalex.org/I119045251"]},{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guancheng Chen","raw_affiliation_strings":["Huaqiao University &amp; Zhejiang Lab, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0001-3468-9913","affiliations":[{"raw_affiliation_string":"Huaqiao University &amp; Zhejiang Lab, Xiamen, China","institution_ids":["https://openalex.org/I119045251","https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352180","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-0011-6260"},"institutions":[{"id":"https://openalex.org/I119045251","display_name":"Huaqiao University","ror":"https://ror.org/03frdh605","country_code":"CN","type":"education","lineage":["https://openalex.org/I119045251"]},{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["Huaqiao University &amp; Zhejiang Lab, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-0011-6260","affiliations":[{"raw_affiliation_string":"Huaqiao University &amp; Zhejiang Lab, Xiamen, China","institution_ids":["https://openalex.org/I119045251","https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5685-3123","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038516431","display_name":"Yiu\u2010ming Cheung","orcid":"https://orcid.org/0000-0001-7629-4648"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiu-ming Cheung","raw_affiliation_strings":["Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-7629-4648","affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021697903","display_name":"Taihao Li","orcid":"https://orcid.org/0000-0003-3279-7125"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taihao Li","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3279-7125","affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7056","last_page":"7064"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"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":0.8076485395431519},{"id":"https://openalex.org/keywords/archetype","display_name":"Archetype","score":0.5666818618774414},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.547612190246582},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5420094728469849},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5418977737426758},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.5047193765640259},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48297443985939026},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4602436423301697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.449409157037735},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.44654515385627747},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4246538281440735},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4233097434043884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34419670701026917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32311367988586426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076485395431519},{"id":"https://openalex.org/C49848784","wikidata":"https://www.wikidata.org/wiki/Q131714","display_name":"Archetype","level":2,"score":0.5666818618774414},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.547612190246582},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5420094728469849},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5418977737426758},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.5047193765640259},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48297443985939026},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4602436423301697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.449409157037735},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.44654515385627747},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4246538281440735},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4233097434043884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34419670701026917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32311367988586426},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611938","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5140599133","display_name":null,"funder_award_id":"12201321","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6515857316","display_name":null,"funder_award_id":"N_HKBU214/21","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320955","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131"},{"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":29,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W2066078528","https://openalex.org/W2096733369","https://openalex.org/W2325939864","https://openalex.org/W2515770085","https://openalex.org/W2595840341","https://openalex.org/W2606377603","https://openalex.org/W2797032258","https://openalex.org/W2798991696","https://openalex.org/W2802864907","https://openalex.org/W2808631503","https://openalex.org/W2962918445","https://openalex.org/W2963026686","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2997819898","https://openalex.org/W3015734344","https://openalex.org/W3034303554","https://openalex.org/W3034725201","https://openalex.org/W3036625283","https://openalex.org/W3048939150","https://openalex.org/W3093411628","https://openalex.org/W3099638501","https://openalex.org/W3108655343","https://openalex.org/W3123318516","https://openalex.org/W3175300676","https://openalex.org/W3177326298","https://openalex.org/W3215742971","https://openalex.org/W4283382486"],"related_works":["https://openalex.org/W3042248303","https://openalex.org/W2971731373","https://openalex.org/W2946570158","https://openalex.org/W2367903128","https://openalex.org/W2372449700","https://openalex.org/W2912650197","https://openalex.org/W2529014963","https://openalex.org/W2366000998","https://openalex.org/W3136706476","https://openalex.org/W627697492"],"abstract_inverted_index":{"Voice-face":[0],"association":[1,214],"is":[2,109,139,163],"generally":[3],"specialized":[4],"as":[5,58],"a":[6,79],"cross-modal":[7,80,202],"cognitive":[8,203],"matching":[9],"problem,":[10],"and":[11,40,144,175,216],"recent":[12],"attention":[13],"has":[14],"been":[15],"paid":[16],"on":[17,51,171],"the":[18,22,35,45,49,62,66,73,122,127,146,168,178,182,186,188,194,208,211,222],"feasibility":[19],"of":[20,37,54,69,121,130,185,201,210],"devising":[21],"computational":[23],"mechanisms":[24],"for":[25,98],"recognizing":[26],"such":[27],"associations.":[28],"Existing":[29],"works":[30],"are":[31],"commonly":[32],"resorting":[33],"to":[34,43,112,125,141,166,197],"combination":[36,63],"contrastive":[38],"learning":[39],"classification-based":[41],"loss":[42],"correlate":[44],"heterogeneous":[46],"datas.":[47,131],"Nevertheless,":[48],"reliance":[50],"typical":[52],"features":[53,71],"each":[55],"category,":[56],"known":[57],"archetypes,":[59],"derived":[60,165],"from":[61,65,154],"suffer":[64],"weak":[67],"invariance":[68],"modality-specific":[70],"within":[72],"same":[74],"identity,":[75],"which":[76,116],"might":[77],"induce":[78],"joint":[81,155,183],"feature":[82,114,156],"space":[83],"with":[84,221],"calibration":[85,115],"deviations.":[86],"To":[87],"tackle":[88],"these":[89],"problems,":[90],"this":[91],"paper":[92],"presents":[93],"an":[94,103,133,159],"efficient":[95,134],"Archetype-agnostic":[96,104],"framework":[97,190,215],"reliable":[99],"voice-face":[100,195,213],"association.":[101],"First,":[102],"Subspace":[105],"Merging":[106],"(AaSM)":[107],"method":[108],"carefully":[110],"designed":[111],"perform":[113],"can":[117,191],"well":[118,192],"get":[119],"rid":[120],"archetype":[123],"dependence":[124],"facilitate":[126],"mutual":[128],"perception":[129],"Further,":[132],"Bilateral":[135],"Connection":[136],"Re-gauging":[137],"scheme":[138],"proposed":[140,189,212],"quantitatively":[142],"screen":[143],"calibrate":[145],"biased":[147],"datas,":[148],"namely":[149],"loose":[150,172],"pairs":[151,174],"that":[152],"deviate":[153],"space.":[157],"Besides,":[158],"Instance":[160],"Equilibrium":[161],"strategy":[162],"dynamically":[164],"optimize":[167],"training":[169],"process":[170],"data":[173,179,196],"significantly":[176],"improve":[177],"utilization.":[180],"Through":[181],"exploitation":[184],"above,":[187],"associate":[193],"benefit":[198],"various":[199],"kinds":[200],"tasks.":[204],"Extensive":[205],"experiments":[206],"verify":[207],"superiorities":[209],"show":[217],"its":[218],"competitive":[219],"performances":[220],"state-of-the-arts.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
