{"id":"https://openalex.org/W4386072006","doi":"https://doi.org/10.1109/cvpr52729.2023.00639","title":"High-Fidelity Generalized Emotional Talking Face Generation with Multi-Modal Emotion Space Learning","display_name":"High-Fidelity Generalized Emotional Talking Face Generation with Multi-Modal Emotion Space Learning","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386072006","doi":"https://doi.org/10.1109/cvpr52729.2023.00639"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.00639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5050543156","display_name":"Chao Xu","orcid":"https://orcid.org/0000-0002-2759-6364"},"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":"Chao Xu","raw_affiliation_strings":["Zhejiang University,APRIL Lab","APRIL Lab, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,APRIL Lab","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"APRIL Lab, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058947127","display_name":"Junwei Zhu","orcid":"https://orcid.org/0000-0001-9846-9656"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwei Zhu","raw_affiliation_strings":["Tencent,Youtu Lab","Youtu Lab, Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent,Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861529","display_name":"Jiangning Zhang","orcid":"https://orcid.org/0000-0001-8891-6766"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangning Zhang","raw_affiliation_strings":["Tencent,Youtu Lab","Youtu Lab, Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent,Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083913830","display_name":"Yue Han","orcid":"https://orcid.org/0000-0003-4494-5455"},"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":"Yue Han","raw_affiliation_strings":["Zhejiang University,APRIL Lab","APRIL Lab, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,APRIL Lab","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"APRIL Lab, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017381951","display_name":"Wenqing Chu","orcid":"https://orcid.org/0000-0003-0816-7975"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqing Chu","raw_affiliation_strings":["Tencent,Youtu Lab","Youtu Lab, Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent,Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029021362","display_name":"Ying Tai","orcid":"https://orcid.org/0000-0002-4665-6852"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Tai","raw_affiliation_strings":["Tencent,Youtu Lab","Youtu Lab, Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent,Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023834700","display_name":"Chengjie Wang","orcid":"https://orcid.org/0000-0003-4216-8090"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"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":"Chengjie Wang","raw_affiliation_strings":["Tencent,Youtu Lab","Shanghai Jiao Tong University","Youtu Lab, Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent,Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Youtu Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100301468","display_name":"Zhifeng Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Xie","raw_affiliation_strings":["Shanghai University"],"affiliations":[{"raw_affiliation_string":"Shanghai University","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100724297","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-4822-8939"},"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":"Yong Liu","raw_affiliation_strings":["Zhejiang University,APRIL Lab","APRIL Lab, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,APRIL Lab","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"APRIL Lab, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5050543156"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":3.6896,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94751004,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6609","last_page":"6619"},"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":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T11448","display_name":"Face recognition and analysis","score":0.9987000226974487,"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":0.9914000034332275,"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":0.7198800444602966},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4891717731952667},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4863065183162689},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.47022223472595215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4496800899505615},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4230853319168091},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4207509160041809},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4156109392642975},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4142424464225769},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4125273823738098},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35764116048812866},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3229180872440338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7198800444602966},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4891717731952667},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4863065183162689},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.47022223472595215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496800899505615},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4230853319168091},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4207509160041809},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4156109392642975},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4142424464225769},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4125273823738098},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35764116048812866},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3229180872440338},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52729.2023.00639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2125389028","https://openalex.org/W2133665775","https://openalex.org/W2157331557","https://openalex.org/W2604379605","https://openalex.org/W2619383789","https://openalex.org/W2745497104","https://openalex.org/W2754447548","https://openalex.org/W2808631503","https://openalex.org/W2952499146","https://openalex.org/W2962785568","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2964449965","https://openalex.org/W2970710980","https://openalex.org/W3008823916","https://openalex.org/W3010434693","https://openalex.org/W3015906192","https://openalex.org/W3019952993","https://openalex.org/W3035574324","https://openalex.org/W3035693354","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3097269285","https://openalex.org/W3099284785","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3122081138","https://openalex.org/W3166396011","https://openalex.org/W3174301209","https://openalex.org/W3174763799","https://openalex.org/W3186090335","https://openalex.org/W3194672963","https://openalex.org/W3195529437","https://openalex.org/W3197199219","https://openalex.org/W3201838419","https://openalex.org/W3204680331","https://openalex.org/W3207849023","https://openalex.org/W3208601549","https://openalex.org/W3209710747","https://openalex.org/W3211147706","https://openalex.org/W3216156094","https://openalex.org/W4200174933","https://openalex.org/W4210657261","https://openalex.org/W4214926101","https://openalex.org/W4224040648","https://openalex.org/W4225456588","https://openalex.org/W4225782468","https://openalex.org/W4226204502","https://openalex.org/W4281730245","https://openalex.org/W4281779270","https://openalex.org/W4286611314","https://openalex.org/W4301206121","https://openalex.org/W4312283676","https://openalex.org/W4312301053","https://openalex.org/W4312444931","https://openalex.org/W4312857984","https://openalex.org/W4313145975","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6678815747","https://openalex.org/W6735927292","https://openalex.org/W6737896281","https://openalex.org/W6739901393","https://openalex.org/W6750008037","https://openalex.org/W6752944736","https://openalex.org/W6765779288","https://openalex.org/W6767264202","https://openalex.org/W6771275388","https://openalex.org/W6774285787","https://openalex.org/W6783376789","https://openalex.org/W6784701471","https://openalex.org/W6785212809","https://openalex.org/W6791353385","https://openalex.org/W6797201126","https://openalex.org/W6803950303","https://openalex.org/W6804128921","https://openalex.org/W6810230290","https://openalex.org/W6810437918","https://openalex.org/W6810828017","https://openalex.org/W6811134278","https://openalex.org/W6811548253"],"related_works":["https://openalex.org/W627697492","https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W4224231624","https://openalex.org/W2332512904"],"abstract_inverted_index":{"Recently,":[0],"emotional":[1],"talking":[2],"face":[3,187],"generation":[4],"has":[5],"received":[6],"considerable":[7],"attention.":[8],"However,":[9],"existing":[10],"methods":[11],"only":[12],"adopt":[13],"one-hot":[14],"coding,":[15],"image,":[16,83],"or":[17,46],"audio":[18,85,135],"as":[19],"emotion":[20,34,67,86,102,110,119,131,180],"conditions,":[21],"thus":[22],"lacking":[23],"flexible":[24,59],"control":[25,181],"in":[26,69,165,179],"practical":[27],"applications":[28],"and":[29,60,72,84,114,133,162,174,182],"failing":[30],"to":[31,37,79,117,128,137,149],"handle":[32],"unseen":[33,118],"styles":[35],"due":[36],"limited":[38],"semantics.":[39],"They":[40],"either":[41],"ignore":[42],"the":[43,47,66,81,130,134,172,183],"one-shot":[44],"setting":[45],"quality":[48],"of":[49,176,185],"generated":[50],"faces.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,64],"propose":[56],"a":[57,89,166],"more":[58],"generalized":[61],"framework.":[62],"Specifically,":[63],"supplement":[65],"style":[68],"text":[70],"prompts":[71],"use":[73],"an":[74,122],"Aligned":[75],"Multi-modal":[76],"Emotion":[77],"encoder":[78],"embed":[80],"text,":[82],"modality":[87,111],"into":[88],"unified":[90],"space,":[91],"which":[92],"inherits":[93],"rich":[94],"semantic":[95],"prior":[96],"from":[97],"CLIP.":[98],"Consequently,":[99],"effective":[100],"multi-modal":[101],"space":[103],"learning":[104],"helps":[105],"our":[106,177],"method":[107,178],"support":[108],"arbitrary":[109,151],"during":[112],"testing":[113],"could":[115],"generalize":[116],"styles.":[120],"Besides,":[121],"Emotion-aware":[123],"Audio-to-3DMM":[124],"Convertor":[125],"is":[126,147],"proposed":[127],"connect":[129],"condition":[132],"sequence":[136],"structural":[138],"representation.":[139],"A":[140],"followed":[141],"style-based":[142],"High-fidelity":[143],"Emotional":[144],"Face":[145],"generator":[146,157],"designed":[148],"generate":[150],"high-resolution":[152],"realistic":[153],"identities.":[154],"Our":[155],"texture":[156],"hierarchically":[158],"learns":[159],"flow":[160],"fields":[161],"animated":[163],"faces":[164],"residual":[167],"manner.":[168],"Extensive":[169],"experiments":[170],"demonstrate":[171],"flexibility":[173],"generalization":[175],"effectiveness":[184],"high-quality":[186],"synthesis.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}