{"id":"https://openalex.org/W4387967909","doi":"https://doi.org/10.1145/3581783.3612587","title":"That's What I Said: Fully-Controllable Talking Face Generation","display_name":"That's What I Said: Fully-Controllable Talking Face Generation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967909","doi":"https://doi.org/10.1145/3581783.3612587"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612587","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612587","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612587","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013499323","display_name":"Youngjoon Jang","orcid":"https://orcid.org/0009-0002-0500-6025"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Youngjoon Jang","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003708446","display_name":"Kyeongha Rho","orcid":"https://orcid.org/0009-0001-6487-5418"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyeongha Rho","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082575036","display_name":"Jongbhin Woo","orcid":"https://orcid.org/0009-0005-4941-6837"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongbin Woo","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035071807","display_name":"Hyeongkeun Lee","orcid":"https://orcid.org/0000-0003-2152-3639"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeongkeun Lee","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049243328","display_name":"Jihwan Park","orcid":"https://orcid.org/0000-0001-9817-0953"},"institutions":[{"id":"https://openalex.org/I49946491","display_name":"Hyundai Motors (South Korea)","ror":"https://ror.org/016kvft77","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522","https://openalex.org/I49946491"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihwan Park","raw_affiliation_strings":["42dot Inc., Hyundai Motor Company, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"42dot Inc., Hyundai Motor Company, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I49946491"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059677906","display_name":"Youshin Lim","orcid":"https://orcid.org/0000-0003-3328-0064"},"institutions":[{"id":"https://openalex.org/I49946491","display_name":"Hyundai Motors (South Korea)","ror":"https://ror.org/016kvft77","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522","https://openalex.org/I49946491"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youshin Lim","raw_affiliation_strings":["42dot Inc., Hyundai Motor Company, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"42dot Inc., Hyundai Motor Company, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I49946491"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053784244","display_name":"Byeong-Yeol Kim","orcid":"https://orcid.org/0000-0001-6019-5047"},"institutions":[{"id":"https://openalex.org/I49946491","display_name":"Hyundai Motors (South Korea)","ror":"https://ror.org/016kvft77","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522","https://openalex.org/I49946491"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeong-Yeol Kim","raw_affiliation_strings":["42dot Inc., Hyundai Motor Company, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"42dot Inc., Hyundai Motor Company, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I49946491"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5013499323"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.857,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75977946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3827","last_page":"3836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9990000128746033,"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":0.9972000122070312,"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":0.7341040372848511},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.6892149448394775},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6411511898040771},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.623590886592865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5974072217941284},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5578048229217529},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5519126653671265},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.45708703994750977},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.44121870398521423},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4260214567184448},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.41271114349365234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32314229011535645},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.2837908864021301},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15008673071861267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341040372848511},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.6892149448394775},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6411511898040771},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.623590886592865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5974072217941284},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5578048229217529},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5519126653671265},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.45708703994750977},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.44121870398521423},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4260214567184448},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.41271114349365234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32314229011535645},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2837908864021301},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15008673071861267},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612587","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612587","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612587","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612587","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387967909.pdf","grobid_xml":"https://content.openalex.org/works/W4387967909.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1569907127","https://openalex.org/W1580389772","https://openalex.org/W1779294284","https://openalex.org/W2077521262","https://openalex.org/W2133665775","https://openalex.org/W2738406145","https://openalex.org/W2808631503","https://openalex.org/W2917887692","https://openalex.org/W2944294033","https://openalex.org/W2949662773","https://openalex.org/W2962785568","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2964449965","https://openalex.org/W2969985801","https://openalex.org/W2979894294","https://openalex.org/W3003162010","https://openalex.org/W3018564516","https://openalex.org/W3019952993","https://openalex.org/W3034211329","https://openalex.org/W3034431451","https://openalex.org/W3035574324","https://openalex.org/W3081492798","https://openalex.org/W3096831136","https://openalex.org/W3101631197","https://openalex.org/W3104792420","https://openalex.org/W3109114891","https://openalex.org/W3109547540","https://openalex.org/W3120163087","https://openalex.org/W3154807520","https://openalex.org/W3174763799","https://openalex.org/W3176913662","https://openalex.org/W3177221875","https://openalex.org/W3178284600","https://openalex.org/W3178406257","https://openalex.org/W3180770160","https://openalex.org/W3182270175","https://openalex.org/W3186090335","https://openalex.org/W3217427959","https://openalex.org/W4200631136","https://openalex.org/W4210657261","https://openalex.org/W4283818626","https://openalex.org/W4295312788","https://openalex.org/W4312444931"],"related_works":["https://openalex.org/W2063547430","https://openalex.org/W2524993630","https://openalex.org/W2607244263","https://openalex.org/W2234430299","https://openalex.org/W2095582735","https://openalex.org/W1831690014","https://openalex.org/W1561022130","https://openalex.org/W2059318893","https://openalex.org/W1965698851","https://openalex.org/W1995263003"],"abstract_inverted_index":{"The":[0,23,42],"goal":[1],"of":[2,105,115],"this":[3,16],"paper":[4],"is":[5,25,44],"to":[6,26,45,122],"synthesise":[7],"talking":[8,83,125],"faces":[9,84],"with":[10,85,155],"controllable":[11,87],"facial":[12,88,135],"motions.":[13],"To":[14,60,112],"achieve":[15],"goal,":[17],"we":[18,65,118],"propose":[19],"two":[20,72],"key":[21],"ideas.":[22],"first":[24,121],"establish":[27],"a":[28,47,124],"canonical":[29],"space":[30,50],"where":[31],"every":[32],"face":[33,126],"has":[34],"the":[35,71,113,120,145],"same":[36],"motion":[37,49],"patterns":[38],"but":[39],"different":[40,73],"identities.":[41],"second":[43],"navigate":[46],"multimodal":[48],"that":[51,97,129],"only":[52],"represents":[53],"motion-related":[54],"features":[55],"while":[56],"eliminating":[57],"identity":[58,62],"information.":[59],"disentangle":[61],"and":[63,90,109,141],"motion,":[64],"introduce":[66],"an":[67],"orthogonality":[68],"constraint":[69],"between":[70],"latent":[74],"spaces.":[75],"From":[76],"this,":[77],"our":[78,98,116],"method":[79,99],"can":[80,130],"generate":[81],"natural-looking":[82],"fully":[86],"attributes":[89],"accurate":[91],"lip":[92],"synchronisation.":[93],"Extensive":[94],"experiments":[95],"demonstrate":[96],"achieves":[100],"state-of-the-art":[101],"results":[102],"in":[103,144],"terms":[104],"both":[106],"visual":[107],"quality":[108],"lip-sync":[110],"score.":[111],"best":[114],"knowledge,":[117],"are":[119],"develop":[123],"generation":[127],"framework":[128],"accurately":[131],"manifest":[132],"full":[133],"target":[134],"motions":[136],"including":[137],"lip,":[138],"head":[139],"pose,":[140],"eye":[142],"movements":[143],"generated":[146],"video":[147,154],"without":[148],"any":[149],"additional":[150],"supervision":[151],"beyond":[152],"RGB":[153],"audio.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}