{"id":"https://openalex.org/W2964559396","doi":"https://doi.org/10.24963/ijcai.2019/129","title":"Talking Face Generation by Conditional Recurrent Adversarial Network","display_name":"Talking Face Generation by Conditional Recurrent Adversarial Network","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2964559396","doi":"https://doi.org/10.24963/ijcai.2019/129","mag":"2964559396"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/129","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/129","pdf_url":"https://www.ijcai.org/proceedings/2019/0129.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0129.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041567418","display_name":"Yang Song","orcid":"https://orcid.org/0000-0003-1283-1672"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yang Song","raw_affiliation_strings":["University of Tennessee, Knoxville","University of Tennessee , Knoxville"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee , Knoxville","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032124903","display_name":"Jingwen Zhu","orcid":"https://orcid.org/0000-0001-7663-2643"},"institutions":[{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]},{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingwen Zhu","raw_affiliation_strings":["Samsung Research America","Samsung Research America#TAB#"],"affiliations":[{"raw_affiliation_string":"Samsung Research America","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]},{"raw_affiliation_string":"Samsung Research America#TAB#","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324967","display_name":"Dawei Li","orcid":"https://orcid.org/0000-0003-0258-1147"},"institutions":[{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]},{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawei Li","raw_affiliation_strings":["Samsung Research America","Samsung Research America#TAB#"],"affiliations":[{"raw_affiliation_string":"Samsung Research America","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]},{"raw_affiliation_string":"Samsung Research America#TAB#","institution_ids":["https://openalex.org/I4210101778","https://openalex.org/I4210133173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068381686","display_name":"Andy Wang","orcid":"https://orcid.org/0000-0001-8689-9624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andy Wang","raw_affiliation_strings":["IBM"],"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072730926","display_name":"Hairong Qi","orcid":"https://orcid.org/0000-0002-2693-5520"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hairong Qi","raw_affiliation_strings":["University of Tennessee, Knoxville","University of Tennessee , Knoxville"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee , Knoxville","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041567418"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":15.9183,"has_fulltext":false,"cited_by_count":179,"citation_normalized_percentile":{"value":0.99524042,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"919","last_page":"925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9977999925613403,"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":0.993399977684021,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8039974570274353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.626405656337738},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5929391384124756},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5908389091491699},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5010044574737549},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.47330227494239807},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46190792322158813},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.459629625082016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42505303025245667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3419637680053711},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.1756114959716797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039974570274353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.626405656337738},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5929391384124756},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5908389091491699},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5010044574737549},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.47330227494239807},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46190792322158813},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.459629625082016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42505303025245667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3419637680053711},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.1756114959716797},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/129","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/129","pdf_url":"https://www.ijcai.org/proceedings/2019/0129.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/129","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/129","pdf_url":"https://www.ijcai.org/proceedings/2019/0129.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964559396.pdf","grobid_xml":"https://content.openalex.org/works/W2964559396.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W137618294","https://openalex.org/W1522301498","https://openalex.org/W2029199293","https://openalex.org/W2116435618","https://openalex.org/W2118688707","https://openalex.org/W2592232824","https://openalex.org/W2615413256","https://openalex.org/W2726515241","https://openalex.org/W2737658251","https://openalex.org/W2739192055","https://openalex.org/W2919046835","https://openalex.org/W2949099979","https://openalex.org/W2963081548","https://openalex.org/W2963092440","https://openalex.org/W2963290645","https://openalex.org/W2964303162","https://openalex.org/W4297772798","https://openalex.org/W4320013936","https://openalex.org/W4394639938"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W4312490297","https://openalex.org/W2062212388"],"abstract_inverted_index":{"Given":[0],"an":[1,6],"arbitrary":[2,7],"face":[3,18,50,113,143],"image":[4,71],"and":[5,39,72,86,139,168,175],"speech":[8],"clip,":[9],"the":[10,16,46,76,96,109,124,132,136,145,152,158],"proposed":[11],"work":[12],"attempts":[13],"to":[14,45,108,122,134,172],"generate":[15],"talking":[17,49,112,142],"video":[19,33,51,114],"with":[20],"accurate":[21,103],"lip":[22,40,104,127,165,174],"synchronization.":[23,128],"Existing":[24],"works":[25],"either":[26],"do":[27],"not":[28],"consider":[29],"temporal":[30,80],"dependency":[31],"across":[32],"frames":[34],"thus":[35,56],"yielding":[36],"abrupt":[37],"facial":[38,176],"movement":[41],"or":[42],"are":[43,93],"limited":[44],"generation":[47,66],"of":[48,90,111,126,141,154,162],"for":[52,79,98],"a":[53,62,88,119],"specific":[54],"person":[55],"lacking":[57],"generalization":[58],"capacity.":[59],"We":[60,129],"propose":[61],"novel":[63],"conditional":[64],"recurrent":[65,77],"network":[67,97,133],"that":[68],"incorporates":[69],"both":[70,84,173],"audio":[73],"features":[74],"in":[75,95,160],"unit":[78],"dependency.":[81],"To":[82],"achieve":[83],"image-":[85],"video-realism,":[87],"pair":[89],"spatial-temporal":[91],"discriminators":[92],"included":[94],"better":[99],"image/video":[100],"quality.":[101],"Since":[102],"synchronization":[105],"is":[106],"essential":[107],"success":[110],"generation,":[115],"we":[116],"also":[117,130],"construct":[118],"lip-reading":[120],"discriminator":[121],"boost":[123],"accuracy":[125],"extend":[131],"model":[135],"natural":[137],"pose":[138],"expression":[140],"on":[144],"Obama":[146],"Dataset.":[147],"Extensive":[148],"experimental":[149],"results":[150],"demonstrate":[151],"superiority":[153],"our":[155],"framework":[156],"over":[157],"state-of-the-arts":[159],"terms":[161],"visual":[163],"quality,":[164],"sync":[166],"accuracy,":[167],"smooth":[169],"transition":[170],"pertaining":[171],"movement.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":42},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}