{"id":"https://openalex.org/W4390190149","doi":"https://doi.org/10.1109/iccvw60793.2023.00320","title":"VAST: Vivify Your Talking Avatar via Zero-Shot Expressive Facial Style Transfer","display_name":"VAST: Vivify Your Talking Avatar via Zero-Shot Expressive Facial Style Transfer","publication_year":2023,"publication_date":"2023-10-02","ids":{"openalex":"https://openalex.org/W4390190149","doi":"https://doi.org/10.1109/iccvw60793.2023.00320"},"language":"en","primary_location":{"id":"doi:10.1109/iccvw60793.2023.00320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw60793.2023.00320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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/A5101849127","display_name":"Liyang Chen","orcid":"https://orcid.org/0000-0001-6985-8281"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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","GB"],"is_corresponding":true,"raw_author_name":"Liyang Chen","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School","Microsoft","Shenzhen International Graduate School, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School","Shenzhen International Graduate School, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102903512","display_name":"Runnan Li","orcid":"https://orcid.org/0000-0002-0922-003X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Runnan Li","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036821828","display_name":"Weihong Bao","orcid":"https://orcid.org/0009-0008-4696-854X"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Weihong Bao","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School","Shenzhen International Graduate School, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103020698","display_name":"Jun Ling","orcid":"https://orcid.org/0000-0001-7260-7141"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Ling","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101522533","display_name":"Xu Tan","orcid":"https://orcid.org/0000-0002-6457-5407"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sheng Zhao","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101849127"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210164937","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.7189,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73572715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2969","last_page":"2979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"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/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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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/avatar","display_name":"Avatar","score":0.7451847195625305},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.7245902419090271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.70757657289505},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6947736740112305},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.548403799533844},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.46695810556411743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4618048071861267},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4535466432571411},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4297640323638916},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41301608085632324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36405616998672485},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3354461193084717},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12534156441688538},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.11054953932762146},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.08140087127685547}],"concepts":[{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.7451847195625305},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.7245902419090271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70757657289505},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6947736740112305},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.548403799533844},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46695810556411743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4618048071861267},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4535466432571411},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4297640323638916},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41301608085632324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36405616998672485},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3354461193084717},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12534156441688538},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.11054953932762146},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.08140087127685547},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw60793.2023.00320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw60793.2023.00320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1922655562","https://openalex.org/W2015143272","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2128019145","https://openalex.org/W2133665775","https://openalex.org/W2162220380","https://openalex.org/W2187089797","https://openalex.org/W2331128040","https://openalex.org/W2484951126","https://openalex.org/W2518172956","https://openalex.org/W2584229793","https://openalex.org/W2594690981","https://openalex.org/W2738406145","https://openalex.org/W2782422271","https://openalex.org/W2944294033","https://openalex.org/W2949662773","https://openalex.org/W2963073614","https://openalex.org/W2964449965","https://openalex.org/W2981263323","https://openalex.org/W3081492798","https://openalex.org/W3086926995","https://openalex.org/W3087121792","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3101631197","https://openalex.org/W3103801904","https://openalex.org/W3104792420","https://openalex.org/W3174763799","https://openalex.org/W3175779516","https://openalex.org/W3186090335","https://openalex.org/W3195529437","https://openalex.org/W3197199219","https://openalex.org/W3204221554","https://openalex.org/W3204715535","https://openalex.org/W3207849023","https://openalex.org/W3208601549","https://openalex.org/W3216942228","https://openalex.org/W4200174933","https://openalex.org/W4200631136","https://openalex.org/W4210657261","https://openalex.org/W4281730245","https://openalex.org/W4283818626","https://openalex.org/W4312444931","https://openalex.org/W4312671789","https://openalex.org/W4382469130","https://openalex.org/W4388739184","https://openalex.org/W4391602018","https://openalex.org/W6637373629","https://openalex.org/W6640090968","https://openalex.org/W6640963894","https://openalex.org/W6674330103","https://openalex.org/W6687045409","https://openalex.org/W6730306933","https://openalex.org/W6739901393","https://openalex.org/W6748181857","https://openalex.org/W6749555683","https://openalex.org/W6765779288","https://openalex.org/W6770208262","https://openalex.org/W6779661269","https://openalex.org/W6849049266"],"related_works":["https://openalex.org/W3138471234","https://openalex.org/W4247958311","https://openalex.org/W4396832849","https://openalex.org/W2785089443","https://openalex.org/W2265117524","https://openalex.org/W4312431072","https://openalex.org/W4399125999","https://openalex.org/W1872262506","https://openalex.org/W2169060180","https://openalex.org/W2642127892"],"abstract_inverted_index":{"Current":[0],"talking":[1,16,152],"face":[2],"generation":[3],"methods":[4],"mainly":[5],"focus":[6],"on":[7,13,110],"speech-lip":[8],"synchronization.":[9],"However,":[10],"insufficient":[11],"investigation":[12],"the":[14,39,42,57,77,97,121,144],"facial":[15,73,83,111,123],"style":[17,51,69,74,93,98,112,124],"leads":[18],"to":[19,29,55,86,100,118,148],"a":[20,68,81,91,133,138,149],"lifeless":[21],"and":[22,37,104,129,157],"monotonous":[23],"avatar.":[24],"Most":[25],"previous":[26],"works":[27],"fail":[28],"imitate":[30],"expressive":[31,103,122],"styles":[32],"from":[33,76,125],"arbitrary":[34,126],"video":[35,79,127],"prompts":[36,128],"ensure":[38],"authenticity":[40,156],"of":[41,64],"generated":[43],"video.":[44],"This":[45],"paper":[46],"proposes":[47],"an":[48],"unsupervised":[49],"variational":[50,92],"transfer":[52,130],"model":[53,62,87,115],"(VAST)":[54],"vivify":[56],"neutral":[58],"photo-realistic":[59],"avatars.":[60],"Our":[61],"consists":[63],"three":[65],"key":[66],"components:":[67],"encoder":[70],"that":[71,95],"extracts":[72],"representations":[75],"given":[78],"prompts;":[80],"hybrid":[82],"expression":[84],"decoder":[85],"accurate":[88],"speech-related":[89],"movements;":[90],"enhancer":[94],"enhances":[96],"space":[99],"be":[101],"highly":[102],"meaningful.":[105],"With":[106],"our":[107,114],"essential":[108],"designs":[109],"learning,":[113],"is":[116],"able":[117],"flexibly":[119],"capture":[120],"it":[131],"onto":[132],"personalized":[134],"image":[135],"renderer":[136],"in":[137],"zero-shot":[139],"manner.":[140],"Experimental":[141],"results":[142],"demonstrate":[143],"proposed":[145],"approach":[146],"contributes":[147],"more":[150],"vivid":[151],"avatar":[153],"with":[154],"higher":[155],"richer":[158],"expressiveness.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}