{"id":"https://openalex.org/W3093450153","doi":"https://doi.org/10.1145/3394171.3413844","title":"Talking Face Generation with Expression-Tailored Generative Adversarial Network","display_name":"Talking Face Generation with Expression-Tailored Generative Adversarial Network","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093450153","doi":"https://doi.org/10.1145/3394171.3413844","mag":"3093450153"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413844","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5023724461","display_name":"Dan Zeng","orcid":"https://orcid.org/0000-0003-1300-1769"},"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":true,"raw_author_name":"Dan Zeng","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102605219","display_name":"Han Liu","orcid":"https://orcid.org/0000-0002-4083-3053"},"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":"Han Liu","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029920666","display_name":"Hui Lin","orcid":"https://orcid.org/0000-0002-6559-2751"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Lin","raw_affiliation_strings":["Shanghai Key Laboratory of Artificial Intelligence in Learning and Cognitive Science, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Artificial Intelligence in Learning and Cognitive Science, Shanghai, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033254559","display_name":"Shiming Ge","orcid":"https://orcid.org/0000-0001-5293-310X"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiming Ge","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023724461"],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":1.5705,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.85824361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1716","last_page":"1724"},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9961000084877014,"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":0.7757440209388733},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.7602050304412842},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6214527487754822},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5793799161911011},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5739335417747498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5455058217048645},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5350450277328491},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5292878746986389},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4780576527118683},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47466161847114563},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4660058617591858},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.4646676480770111},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40907788276672363},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09555104374885559}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757440209388733},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.7602050304412842},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6214527487754822},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5793799161911011},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5739335417747498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5455058217048645},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5350450277328491},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5292878746986389},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4780576527118683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47466161847114563},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4660058617591858},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.4646676480770111},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40907788276672363},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09555104374885559},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413844","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2015143272","https://openalex.org/W2030931454","https://openalex.org/W2513140567","https://openalex.org/W2560474170","https://openalex.org/W2737047298","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2766261529","https://openalex.org/W2788865504","https://openalex.org/W2795089319","https://openalex.org/W2799041689","https://openalex.org/W2804600264","https://openalex.org/W2804619907","https://openalex.org/W2883861033","https://openalex.org/W2895115565","https://openalex.org/W2899388690","https://openalex.org/W2900597592","https://openalex.org/W2904622387","https://openalex.org/W2914217321","https://openalex.org/W2941044098","https://openalex.org/W2944294033","https://openalex.org/W2949662773","https://openalex.org/W2962692288","https://openalex.org/W2962785568","https://openalex.org/W2963066677","https://openalex.org/W2963073614","https://openalex.org/W2963092440","https://openalex.org/W2963290645","https://openalex.org/W2963408477","https://openalex.org/W2963507023","https://openalex.org/W2963524571","https://openalex.org/W2963767194","https://openalex.org/W2963981733","https://openalex.org/W2964045355","https://openalex.org/W2970955473","https://openalex.org/W2972563022","https://openalex.org/W2979894294","https://openalex.org/W2981263323","https://openalex.org/W2989044841","https://openalex.org/W2991327923","https://openalex.org/W2995396423","https://openalex.org/W2999748665","https://openalex.org/W3006410788","https://openalex.org/W3014206170","https://openalex.org/W3022628827","https://openalex.org/W3104792420","https://openalex.org/W3106277454","https://openalex.org/W4403242122"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W4380714744","https://openalex.org/W2387995142","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2964074194","https://openalex.org/W2995777218","https://openalex.org/W2366944513"],"abstract_inverted_index":{"A":[0],"key":[1],"of":[2,54,71,102,118,145,170],"automatically":[3],"generating":[4,174],"vivid":[5],"talking":[6,51,59,178],"faces":[7,119],"is":[8,84,112],"to":[9,21,46,86,129],"synthesize":[10],"identity-preserving":[11],"natural":[12],"facial":[13,149],"expressions":[14],"beyond":[15],"audio-lip":[16,99],"synchronization,":[17],"which":[18],"usually":[19],"need":[20],"disentangle":[22,87],"the":[23,76,91,134,168],"informative":[24],"features":[25],"from":[26,58,90],"multiple":[27],"modals":[28],"and":[29,66,120,133,148,162],"then":[30],"fuse":[31],"them":[32],"together.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"propose":[38],"an":[39,48,68],"end-to-end":[40],"Expression-Tailored":[41],"Generative":[42],"Adversarial":[43],"Network":[44],"(ET-GAN)":[45],"generate":[47],"expression":[49,77,146,159],"enriched":[50],"face":[52,60,179],"video":[53,70],"arbitrary":[55,72],"identity.":[56],"Different":[57],"generation":[61],"based":[62],"on":[63,156],"identity":[64,73,107,110],"image":[65,105],"audio,":[67],"expressional":[69,93,177],"serves":[74],"as":[75,106],"source":[78],"in":[79,173],"our":[80,171],"approach.":[81],"Expression":[82],"encoder":[83,97,111],"proposed":[85,113],"expression-tailored":[88],"representation":[89],"guiding":[92],"video,":[94],"while":[95],"audio":[96],"disentangles":[98],"representation.":[100,124],"Instead":[101],"using":[103],"single":[104],"input,":[108],"multi-image":[109],"by":[114],"learning":[115],"different":[116],"views":[117],"merging":[121],"a":[122,139],"unified":[123],"Multiple":[125],"discriminators":[126],"are":[127],"exploited":[128],"keep":[130],"both":[131],"image-aware":[132],"video-aware":[135],"realistic":[136],"details,":[137],"including":[138],"spatial-temporal":[140],"discriminator":[141],"for":[142],"visual":[143],"continuity":[144],"synthesis":[147],"movements.":[150],"We":[151],"conduct":[152],"extensive":[153],"experimental":[154],"evaluations":[155],"quantitative":[157],"metrics,":[158],"retention":[160],"quality":[161,176],"audio-visual":[163],"synchronization.":[164],"The":[165],"results":[166],"show":[167],"effectiveness":[169],"ET-GAN":[172],"high":[175],"videos":[180],"against":[181],"existing":[182],"state-of-the-arts.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}