{"id":"https://openalex.org/W2739192055","doi":"https://doi.org/10.1145/3072959.3073658","title":"Audio-driven facial animation by joint end-to-end learning of pose and emotion","display_name":"Audio-driven facial animation by joint end-to-end learning of pose and emotion","publication_year":2017,"publication_date":"2017-07-20","ids":{"openalex":"https://openalex.org/W2739192055","doi":"https://doi.org/10.1145/3072959.3073658","mag":"2739192055"},"language":"en","primary_location":{"id":"doi:10.1145/3072959.3073658","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3072959.3073658","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-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/A5004093189","display_name":"Tero Karras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tero Karras","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080133323","display_name":"Timo Aila","orcid":"https://orcid.org/0000-0002-9437-4438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timo Aila","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029831111","display_name":"Samuli Laine","orcid":"https://orcid.org/0000-0002-0903-3197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuli Laine","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027815620","display_name":"Antti Herva","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antti Herva","raw_affiliation_strings":["Remedy Entertainment"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Remedy Entertainment","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103009697","display_name":"Jaakko Lehtinen","orcid":"https://orcid.org/0000-0001-9418-4944"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI","GB"],"is_corresponding":false,"raw_author_name":"Jaakko Lehtinen","raw_affiliation_strings":["NVIDIA and Aalto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA and Aalto University","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.8999,"has_fulltext":false,"cited_by_count":430,"citation_normalized_percentile":{"value":0.98893486,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"36","issue":"4","first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9993000030517578,"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":0.9993000030517578,"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/T12290","display_name":"Human Motion and Animation","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9926999807357788,"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":0.8280409574508667},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5949454307556152},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5189095139503479},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.51514732837677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.492870569229126},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4870145916938782},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47552254796028137},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3632373809814453},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34555870294570923},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1630536913871765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8280409574508667},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5949454307556152},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5189095139503479},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.51514732837677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.492870569229126},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4870145916938782},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47552254796028137},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3632373809814453},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34555870294570923},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1630536913871765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3072959.3073658","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3072959.3073658","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568},{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W123891002","https://openalex.org/W788203010","https://openalex.org/W1485743559","https://openalex.org/W1489712442","https://openalex.org/W1522301498","https://openalex.org/W1547376871","https://openalex.org/W1554803342","https://openalex.org/W1667652561","https://openalex.org/W1779294284","https://openalex.org/W1788348338","https://openalex.org/W1822526425","https://openalex.org/W1985447466","https://openalex.org/W1987709386","https://openalex.org/W2000911139","https://openalex.org/W2010284423","https://openalex.org/W2021992838","https://openalex.org/W2024536104","https://openalex.org/W2032693983","https://openalex.org/W2038548569","https://openalex.org/W2064400654","https://openalex.org/W2071096833","https://openalex.org/W2082942761","https://openalex.org/W2095705004","https://openalex.org/W2104480821","https://openalex.org/W2115276447","https://openalex.org/W2115402659","https://openalex.org/W2120654454","https://openalex.org/W2122007052","https://openalex.org/W2122295613","https://openalex.org/W2125766142","https://openalex.org/W2126972963","https://openalex.org/W2128546114","https://openalex.org/W2129360799","https://openalex.org/W2134331998","https://openalex.org/W2143640516","https://openalex.org/W2157986450","https://openalex.org/W2160551639","https://openalex.org/W2168961642","https://openalex.org/W2170653751","https://openalex.org/W2295661697","https://openalex.org/W2338517121","https://openalex.org/W2384495648","https://openalex.org/W2468212864","https://openalex.org/W2515372520","https://openalex.org/W2949117887","https://openalex.org/W2949382160","https://openalex.org/W2949608135","https://openalex.org/W3006295631","https://openalex.org/W3114284325","https://openalex.org/W6788119825"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2532377291","https://openalex.org/W2989004599","https://openalex.org/W2535923857","https://openalex.org/W1976926596","https://openalex.org/W3094080214","https://openalex.org/W2156310872","https://openalex.org/W2356609371"],"abstract_inverted_index":{"We":[0,82],"present":[1],"a":[2,26,37,43,112,138],"machine":[3],"learning":[4],"technique":[5],"for":[6,74],"driving":[7],"3D":[8,33],"facial":[9,52],"animation":[10,91],"by":[11,58],"audio":[12,60,124],"input":[13,29],"in":[14,51],"real":[15],"time":[16],"and":[17,40,153],"with":[18,86,123,128,137],"low":[19],"latency.":[20],"Our":[21],"deep":[22],"neural":[23],"network":[24,85],"learns":[25],"mapping":[27],"from":[28,125],"waveforms":[30],"to":[31,106,145],"the":[32,49,59,64,75,79,108],"vertex":[34],"coordinates":[35],"of":[36,78,89,111],"face":[38,80],"model,":[39],"simultaneously":[41],"discovers":[42],"compact,":[44],"latent":[45,65],"code":[46,66],"that":[47,54],"disambiguates":[48],"variations":[50],"expression":[53],"cannot":[55],"be":[56,68],"explained":[57],"alone.":[61],"During":[62],"inference,":[63],"can":[67],"used":[69],"as":[70,134],"an":[71],"intuitive":[72],"control":[73],"emotional":[76],"state":[77],"puppet.":[81],"train":[83],"our":[84,102,115],"3--5":[87],"minutes":[88],"high-quality":[90],"data":[92],"obtained":[93],"using":[94],"traditional,":[95],"vision-based":[96],"performance":[97],"capture":[98],"methods.":[99],"Even":[100],"though":[101],"primary":[103],"goal":[104],"is":[105],"model":[107,116],"speaking":[109],"style":[110],"single":[113],"actor,":[114],"yields":[117],"reasonable":[118],"results":[119,142],"even":[120],"when":[121],"driven":[122],"other":[126],"speakers":[127],"different":[129],"gender,":[130],"accent,":[131],"or":[132],"language,":[133],"we":[135],"demonstrate":[136],"user":[139],"study.":[140],"The":[141],"are":[143],"applicable":[144],"in-game":[146],"dialogue,":[147],"low-cost":[148],"localization,":[149],"virtual":[150],"reality":[151],"avatars,":[152],"telepresence.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":56},{"year":2024,"cited_by_count":72},{"year":2023,"cited_by_count":73},{"year":2022,"cited_by_count":47},{"year":2021,"cited_by_count":55},{"year":2020,"cited_by_count":47},{"year":2019,"cited_by_count":43},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}