{"id":"https://openalex.org/W3016125456","doi":"https://doi.org/10.1109/icassp40776.2020.9053608","title":"Cross-VAE: Towards Disentangling Expression from Identity For Human Faces","display_name":"Cross-VAE: Towards Disentangling Expression from Identity For Human Faces","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016125456","doi":"https://doi.org/10.1109/icassp40776.2020.9053608","mag":"3016125456"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5017383334","display_name":"Haozhe Wu","orcid":"https://orcid.org/0000-0002-3036-6930"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haozhe Wu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405572","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0002-7336-4003"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075290241","display_name":"Lingxi Xie","orcid":"https://orcid.org/0000-0003-4831-9451"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Lingxi Xie","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766907","display_name":"Guo-Jun Qi","orcid":"https://orcid.org/0000-0003-3508-1851"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guojun Qi","raw_affiliation_strings":["Futurewei Technologies"],"affiliations":[{"raw_affiliation_string":"Futurewei Technologies","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057896400","display_name":"Yuanchun Shi","orcid":"https://orcid.org/0000-0003-2273-6927"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchun Shi","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393506","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-7252-5047"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017383334"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5862,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.68083283,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10057","display_name":"Face and Expression Recognition","score":0.9998000264167786,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5255255103111267},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5239022970199585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5188016295433044},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.44218340516090393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34331679344177246},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.11130711436271667},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09449762105941772},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.07236000895500183}],"concepts":[{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5255255103111267},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5239022970199585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5188016295433044},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.44218340516090393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34331679344177246},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.11130711436271667},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09449762105941772},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.07236000895500183},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W132448360","https://openalex.org/W1509966554","https://openalex.org/W1522301498","https://openalex.org/W1691728462","https://openalex.org/W1959608418","https://openalex.org/W2035372623","https://openalex.org/W2103943262","https://openalex.org/W2108598243","https://openalex.org/W2134860945","https://openalex.org/W2188365844","https://openalex.org/W2194775991","https://openalex.org/W2198512331","https://openalex.org/W2217426128","https://openalex.org/W2341528187","https://openalex.org/W2604209953","https://openalex.org/W2621357189","https://openalex.org/W2730601341","https://openalex.org/W2737047298","https://openalex.org/W2737398044","https://openalex.org/W2738672149","https://openalex.org/W2753738274","https://openalex.org/W2785519580","https://openalex.org/W2798583514","https://openalex.org/W2890159224","https://openalex.org/W2902598059","https://openalex.org/W2903794034","https://openalex.org/W2963010714","https://openalex.org/W2963104724","https://openalex.org/W2963112684","https://openalex.org/W2963226019","https://openalex.org/W2963264829","https://openalex.org/W2963290645","https://openalex.org/W2963366547","https://openalex.org/W2964121744","https://openalex.org/W3101998545","https://openalex.org/W4295112158","https://openalex.org/W6630649318","https://openalex.org/W6631190155","https://openalex.org/W6637412569","https://openalex.org/W6640963894","https://openalex.org/W6687045409","https://openalex.org/W6687716273","https://openalex.org/W6718140377","https://openalex.org/W6735583111","https://openalex.org/W6744627333","https://openalex.org/W6745687250","https://openalex.org/W6748223763","https://openalex.org/W6754663736","https://openalex.org/W6756966509","https://openalex.org/W7075712485"],"related_works":["https://openalex.org/W2103413230","https://openalex.org/W2048360808","https://openalex.org/W2355490025","https://openalex.org/W2057064510","https://openalex.org/W2155074382","https://openalex.org/W2908959303","https://openalex.org/W2410151940","https://openalex.org/W2013053025","https://openalex.org/W4231184624","https://openalex.org/W2035926100"],"abstract_inverted_index":{"Facial":[0],"expression":[1,16,48,58,92],"and":[2,39,59,128,172],"identity":[3,18,60],"are":[4,43,118],"two":[5,114,152],"independent":[6,110],"yet":[7],"intertwined":[8],"components":[9],"for":[10,47,175],"representing":[11],"a":[12,77,133],"face.":[13],"For":[14],"facial":[15,176],"recognition,":[17],"can":[19,156],"contaminate":[20],"the":[21,97,113,138,146,149,180],"training":[22,135],"procedure":[23,136],"by":[24],"providing":[25],"tangled":[26],"but":[27],"irrelevant":[28],"information.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"propose":[34],"to":[35,72,76,85,90,125],"learn":[36],"clearly":[37],"disentangled":[38,127,173],"discriminative":[40],"features":[41,174],"that":[42,112,163],"invariant":[44],"of":[45,56,101,140,148,169,188,194],"identities":[46],"recognition.":[49],"However,":[50],"such":[51],"disentanglement":[52],"normally":[53],"requires":[54],"annotations":[55],"both":[57,122],"on":[61,108,190],"one":[62],"large":[63],"dataset,":[64],"which":[65,82],"is":[66,71,83,106,143,167],"often":[67],"unavailable.":[68],"Our":[69],"solution":[70],"extend":[73],"conditional":[74],"VAE":[75],"crossed":[78],"version":[79],"named":[80],"Cross-VAE,":[81],"able":[84],"use":[86],"partially":[87,153],"labeled":[88,154],"data":[89],"disentangle":[91],"from":[93],"identity.":[94],"We":[95],"emphasis":[96],"following":[98],"novel":[99],"characteristics":[100],"our":[102,164,183],"Cross-VAE:":[103],"(1)":[104],"It":[105,131],"based":[107],"an":[109,186],"assumption":[111],"latent":[115],"representations'":[116],"distributions":[117],"orthogonal.":[119],"This":[120],"ensures":[121],"encoded":[123],"representations":[124],"be":[126,157],"expressive.":[129],"(2)":[130],"utilizes":[132],"symmetric":[134],"where":[137],"output":[139],"each":[141],"encoder":[142],"fed":[144],"as":[145],"condition":[147],"other.":[150],"Thus":[151],"sets":[155],"jointly":[158],"used.":[159],"Extensive":[160],"experiments":[161],"show":[162],"proposed":[165],"method":[166],"capable":[168],"encoding":[170],"expressive":[171],"expression.":[177],"Compared":[178],"with":[179],"baseline":[181],"methods,":[182],"model":[184],"shows":[185],"improvement":[187],"3.56%":[189],"average":[191],"in":[192],"terms":[193],"accuracy.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}