{"id":"https://openalex.org/W4415708722","doi":"https://doi.org/10.1109/icme59968.2025.11209335","title":"Audio-Driven Emotion-Aware 3D Talking Face Generation from Single Image","display_name":"Audio-Driven Emotion-Aware 3D Talking Face Generation from Single Image","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708722","doi":"https://doi.org/10.1109/icme59968.2025.11209335"},"language":"en","primary_location":{"id":"doi:10.1109/icme59968.2025.11209335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":null,"display_name":"Chun-Shuo Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun-Shuo Qiu","raw_affiliation_strings":["Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632772","display_name":"Fenglin Liu","orcid":"https://orcid.org/0000-0001-7715-5228"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng-Lin Liu","raw_affiliation_strings":["Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616578","display_name":"Hongbo Fu","orcid":"https://orcid.org/0000-0001-5542-9654"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongbo Fu","raw_affiliation_strings":["Hong Kong University of Science and Technologyy,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technologyy,Hong Kong,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403428","display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0002-0343-3499"},"institutions":[{"id":"https://openalex.org/I119203015","display_name":"Shandong University of Technology","ror":"https://ror.org/02mr3ar13","country_code":"CN","type":"education","lineage":["https://openalex.org/I119203015"]},{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]},{"id":"https://openalex.org/I83776822","display_name":"Shandong Institute of Business and Technology","ror":"https://ror.org/03rrkrc24","country_code":"CN","type":"education","lineage":["https://openalex.org/I83776822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":["Shandong Technology and Business University,Shandong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Technology and Business University,Shandong,China","institution_ids":["https://openalex.org/I83776822","https://openalex.org/I119203015","https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091525681","display_name":"Yan\u2010Pei Cao","orcid":"https://orcid.org/0000-0002-0416-4374"},"institutions":[{"id":"https://openalex.org/I4210107386","display_name":"V\u00e4stmanlands sjukhus V\u00e4ster\u00e5s","ror":"https://ror.org/01qh83x04","country_code":"SE","type":"healthcare","lineage":["https://openalex.org/I4210107386"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yan-Pei Cao","raw_affiliation_strings":["VAST,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VAST,Beijing,China","institution_ids":["https://openalex.org/I4210107386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067850699","display_name":"Yu\u2010Kun Lai","orcid":"https://orcid.org/0000-0002-2094-5680"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yu-Kun Lai","raw_affiliation_strings":["School of Computer Science and Informatics, Cardiff University,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University,UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100629376","display_name":"Lin Gao","orcid":"https://orcid.org/0000-0002-1021-8148"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Gao","raw_affiliation_strings":["Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.5278000235557556,"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":0.5278000235557556,"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":0.4447999894618988,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/motion","display_name":"Motion (physics)","score":0.652899980545044},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6349999904632568},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5960000157356262},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5293999910354614},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5288000106811523},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5163999795913696},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.41359999775886536},{"id":"https://openalex.org/keywords/match-moving","display_name":"Match moving","score":0.36169999837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712000012397766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7365000247955322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6771000027656555},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.652899980545044},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6349999904632568},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5960000157356262},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5293999910354614},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.36169999837875366},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C174493125","wikidata":"https://www.wikidata.org/wiki/Q1073461","display_name":"Quarter-pixel motion","level":3,"score":0.3174999952316284},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icme59968.2025.11209335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:179565","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169680","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169680","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"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"},{"id":"https://openalex.org/F4320325902","display_name":"Beijing Municipal Science and Technology Commission","ror":null},{"id":"https://openalex.org/F4320334111","display_name":"Innovation Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2970710980","https://openalex.org/W3099284785","https://openalex.org/W3186090335","https://openalex.org/W3197199219","https://openalex.org/W3211147706","https://openalex.org/W4200150166","https://openalex.org/W4200631136","https://openalex.org/W4210657261","https://openalex.org/W4281730245","https://openalex.org/W4310380504","https://openalex.org/W4312453532","https://openalex.org/W4321020813","https://openalex.org/W4382469130","https://openalex.org/W4385490328","https://openalex.org/W4386072021","https://openalex.org/W4386075823","https://openalex.org/W4386076259","https://openalex.org/W4387717549","https://openalex.org/W4387967971","https://openalex.org/W4390872116","https://openalex.org/W4390872769","https://openalex.org/W4396642496","https://openalex.org/W4399695991","https://openalex.org/W4400403028","https://openalex.org/W4402422516","https://openalex.org/W4404404002","https://openalex.org/W4404525697"],"related_works":[],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,46,53,139,162],"face":[2,47,163],"generation":[3,48],"from":[4,55,104],"a":[5,10,40,70,91,101,123,161],"single":[6],"source":[7],"image":[8],"is":[9,111,177],"popular":[11],"research":[12],"topic.":[13],"There":[14],"still":[15],"exist":[16],"many":[17],"challenges":[18],"for":[19],"its":[20],"practical":[21],"applications,":[22],"e.g.,":[23],"diverse":[24],"motion":[25,63,72,84,92,96,144,152,185],"generation,":[26],"effective":[27],"emotional":[28,166],"control,":[29],"and":[30,82,118,145,154,184,191],"large":[31],"view":[32,190],"angle":[33],"changes.":[34],"In":[35],"this":[36],"work,":[37],"we":[38,68,128,158],"propose":[39],"novel":[41,169,192],"one-shot":[42],"emotion-controllable":[43,131],"audio-driven":[44],"3D":[45,102,132],"framework,":[49],"which":[50,87],"creates":[51],"free-view":[52,138],"videos":[54,140],"one":[56,105],"reference":[57,106],"image.":[58],"Firstly,":[59],"to":[60,74,94,99,113,136,149],"synchronize":[61],"the":[62,65,76,79,142,150],"with":[64,122,164],"input":[66,80],"audio,":[67],"use":[69],"transformer-based":[71],"generator":[73,135],"capture":[75],"context":[77],"of":[78,179],"audio":[81],"predict":[83],"coefficient":[85],"sequences,":[86],"are":[88],"leveraged":[89],"by":[90],"encoder":[93,110],"extract":[95,114],"codes.":[97,147],"Meanwhile,":[98],"reconstruct":[100],"portrait":[103,133],"image,":[107],"an":[108,115,130],"identity":[109,116,146,156],"utilized":[112],"code":[117],"generate":[119],"emotion-dependent":[120],"appearance":[121],"specific":[124],"emotion":[125],"label.":[126],"Finally,":[127],"introduce":[129],"video":[134],"synthesize":[137],"using":[141],"disentangled":[143],"Thanks":[148],"audio-synchronized":[151],"codes":[153],"emotion-aware":[155],"code,":[157],"can":[159],"render":[160],"realistic":[165],"expressions":[167],"in":[168,187],"views.":[170,193],"Extensive":[171],"experiments":[172],"show":[173],"that":[174],"our":[175],"method":[176],"capable":[178],"maintaining":[180],"superior":[181],"visual":[182],"performance":[183],"accuracy":[186],"both":[188],"front":[189]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}