{"id":"https://openalex.org/W4312894597","doi":"https://doi.org/10.1109/tvcg.2022.3230541","title":"Personalized Audio-Driven 3D Facial Animation via Style-Content Disentanglement","display_name":"Personalized Audio-Driven 3D Facial Animation via Style-Content Disentanglement","publication_year":2022,"publication_date":"2022-12-19","ids":{"openalex":"https://openalex.org/W4312894597","doi":"https://doi.org/10.1109/tvcg.2022.3230541","pmid":"https://pubmed.ncbi.nlm.nih.gov/37015450"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2022.3230541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2022.3230541","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5032863170","display_name":"Yujin Chai","orcid":"https://orcid.org/0000-0002-5525-6527"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yujin Chai","raw_affiliation_strings":["State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060286507","display_name":"Tianjia Shao","orcid":"https://orcid.org/0000-0001-5485-3752"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianjia Shao","raw_affiliation_strings":["State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004008347","display_name":"Yanlin Weng","orcid":"https://orcid.org/0000-0001-5223-4253"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlin Weng","raw_affiliation_strings":["State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027671723","display_name":"Kun Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":["State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032863170"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.9059,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75560484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"30","issue":"3","first_page":"1803","last_page":"1820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9954000115394592,"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":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8190839886665344},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6842198967933655},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5580501556396484},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5046981573104858},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4969690144062042},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4605533182621002},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.45418065786361694},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.42459720373153687},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.42134395241737366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40828990936279297},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.38195884227752686},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3550504148006439},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.17108798027038574},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.16788440942764282},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1544802486896515},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.08258414268493652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190839886665344},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6842198967933655},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5580501556396484},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5046981573104858},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4969690144062042},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4605533182621002},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.45418065786361694},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.42459720373153687},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.42134395241737366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40828990936279297},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.38195884227752686},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3550504148006439},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.17108798027038574},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.16788440942764282},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1544802486896515},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.08258414268493652},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2022.3230541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2022.3230541","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:37015450","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37015450","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5699999928474426},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1922655562","https://openalex.org/W2038548569","https://openalex.org/W2064400654","https://openalex.org/W2143640516","https://openalex.org/W2289286917","https://openalex.org/W2468212864","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2745771616","https://openalex.org/W2769666294","https://openalex.org/W2804619907","https://openalex.org/W2888823109","https://openalex.org/W2895226286","https://openalex.org/W2942074357","https://openalex.org/W2952056941","https://openalex.org/W2963290645","https://openalex.org/W2963800363","https://openalex.org/W2971634123","https://openalex.org/W2981263323","https://openalex.org/W2997233412","https://openalex.org/W3010434693","https://openalex.org/W3019952993","https://openalex.org/W3025521275","https://openalex.org/W3034211329","https://openalex.org/W3087121792","https://openalex.org/W3097792222","https://openalex.org/W3109114891","https://openalex.org/W3154411171","https://openalex.org/W3159890710","https://openalex.org/W3162071730","https://openalex.org/W3174763799","https://openalex.org/W3180794345","https://openalex.org/W3186090335","https://openalex.org/W3197199219","https://openalex.org/W3200819848","https://openalex.org/W3202128205","https://openalex.org/W3207849023","https://openalex.org/W3208601549","https://openalex.org/W3210676520","https://openalex.org/W4200630629","https://openalex.org/W4210657261","https://openalex.org/W4226204502","https://openalex.org/W6605591784","https://openalex.org/W6631190155","https://openalex.org/W6640090968","https://openalex.org/W6734074887","https://openalex.org/W6739901393","https://openalex.org/W6766759079","https://openalex.org/W6774285787","https://openalex.org/W6811548253"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2532377291","https://openalex.org/W1976926596","https://openalex.org/W2989004599","https://openalex.org/W3094080214","https://openalex.org/W2535923857","https://openalex.org/W2156310872","https://openalex.org/W2356609371"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,15,28,56,73,79,109,154],"learning-based":[3],"approach":[4,180],"for":[5,64],"generating":[6],"3D":[7,172],"facial":[8,95,120,173],"animations":[9],"with":[10,153,164,176],"the":[11,36,51,84,87,105,141,147,159],"motion":[12],"style":[13,24,89,100,115,134,161],"of":[14,50,78,146],"specific":[16],"subject":[17,23,88],"from":[18,27,35,75,119],"arbitrary":[19,165],"audio":[20,166],"inputs.":[21],"The":[22,122],"is":[25,124,132,143,162],"learned":[26],"video":[29,53,76],"clip":[30],"(1-2":[31],"minutes)":[32],"either":[33],"downloaded":[34],"Internet":[37],"or":[38,101],"captured":[39],"through":[40],"an":[41],"ordinary":[42],"camera.":[43],"Traditional":[44],"methods":[45],"often":[46],"require":[47],"many":[48],"hours":[49],"subject's":[52],"to":[54,71,98,168],"learn":[55],"robust":[57],"audio-driven":[58,171],"model":[59,74],"and":[60,90,116,140,150,185,194],"are":[61],"thus":[62],"unsuitable":[63],"this":[65],"task.":[66],"Recent":[67],"research":[68],"efforts":[69],"aim":[70],"train":[72],"collections":[77],"few":[80],"subjects":[81],"but":[82],"ignore":[83],"discrimination":[85],"between":[86,136],"underlying":[91],"speech":[92,117],"content":[93,118],"within":[94],"motions,":[96],"leading":[97],"inaccurate":[99],"articulation.":[102],"To":[103],"solve":[104],"problem,":[106],"we":[107],"propose":[108],"novel":[110,128],"framework":[111],"that":[112],"disentangles":[113],"subject-specific":[114],"motions.":[121],"disentanglement":[123],"enabled":[125],"by":[126],"two":[127,137],"training":[129,145],"mechanisms.":[130],"One":[131],"two-pass":[133],"swapping":[135],"random":[138],"subjects,":[139],"other":[142],"joint":[144],"decomposition":[148],"network":[149,152],"audio-to-motion":[151],"shared":[155],"decoder.":[156],"After":[157],"training,":[158],"disentangled":[160],"combined":[163],"inputs":[167],"generate":[169],"stylized":[170],"animations.":[174],"Compared":[175],"start-of-the-art":[177],"methods,":[178],"our":[179],"achieves":[181],"better":[182],"results":[183],"qualitatively":[184],"quantitatively,":[186],"especially":[187],"in":[188],"difficult":[189],"cases":[190],"like":[191],"bilabial":[192,195],"plosive":[193],"nasal":[196],"phonemes.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}