{"id":"https://openalex.org/W2895226286","doi":"https://doi.org/10.1145/3242969.3243017","title":"End-to-end Learning for 3D Facial Animation from Speech","display_name":"End-to-end Learning for 3D Facial Animation from Speech","publication_year":2018,"publication_date":"2018-10-02","ids":{"openalex":"https://openalex.org/W2895226286","doi":"https://doi.org/10.1145/3242969.3243017","mag":"2895226286"},"language":"en","primary_location":{"id":"doi:10.1145/3242969.3243017","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3243017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","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/A5017287333","display_name":"Hai Pham","orcid":"https://orcid.org/0000-0001-9391-5514"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hai Xuan Pham","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384201","display_name":"Yuting Wang","orcid":"https://orcid.org/0000-0002-1562-2764"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuting Wang","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020368096","display_name":"Vladimir Pavlovi\u0107","orcid":"https://orcid.org/0000-0003-3979-1236"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vladimir Pavlovic","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017287333"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":2.0892,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.90872066,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"361","last_page":"365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","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/T11448","display_name":"Face recognition and analysis","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/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9764000177383423,"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":0.7635465860366821},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.6610829830169678},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6522781848907471},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6480112075805664},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6424026489257812},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5960485935211182},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5545385479927063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5123201608657837},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.4937065541744232},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.46940577030181885},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.46122485399246216},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44875723123550415},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42674708366394043},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.39898374676704407},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3029435873031616},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.2057875096797943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635465860366821},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.6610829830169678},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6522781848907471},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6480112075805664},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6424026489257812},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5960485935211182},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5545385479927063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123201608657837},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.4937065541744232},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.46940577030181885},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46122485399246216},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44875723123550415},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42674708366394043},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.39898374676704407},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3029435873031616},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2057875096797943},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3242969.3243017","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3243017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W34110307","https://openalex.org/W71477782","https://openalex.org/W219197677","https://openalex.org/W1482998036","https://openalex.org/W1493267010","https://openalex.org/W1538131130","https://openalex.org/W1542280630","https://openalex.org/W1600744878","https://openalex.org/W1779294284","https://openalex.org/W1924770834","https://openalex.org/W1995562189","https://openalex.org/W2017107803","https://openalex.org/W2033310064","https://openalex.org/W2036242736","https://openalex.org/W2043440654","https://openalex.org/W2064400654","https://openalex.org/W2064675550","https://openalex.org/W2102003408","https://openalex.org/W2107813907","https://openalex.org/W2113713975","https://openalex.org/W2114336453","https://openalex.org/W2120654454","https://openalex.org/W2134973740","https://openalex.org/W2142487393","https://openalex.org/W2147885303","https://openalex.org/W2150133190","https://openalex.org/W2155273149","https://openalex.org/W2163334800","https://openalex.org/W2237250383","https://openalex.org/W2296650210","https://openalex.org/W2398826216","https://openalex.org/W2399733683","https://openalex.org/W2566655602","https://openalex.org/W2608566907","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2745771616","https://openalex.org/W2963175699","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2295574089","https://openalex.org/W2350195158","https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W1792455311","https://openalex.org/W2055569256","https://openalex.org/W4241846838","https://openalex.org/W4234707920","https://openalex.org/W136487047","https://openalex.org/W2166970146"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,28,38,118,139,151],"deep":[3,16,46],"learning":[4],"framework":[5],"for":[6],"real-time":[7],"speech-driven":[8],"3D":[9,39],"facial":[10,32,72,112,129,155],"animation":[11],"from":[12],"speech":[13,25],"audio.":[14],"Our":[15],"neural":[17],"network":[18],"directly":[19],"maps":[20],"an":[21],"input":[22],"sequence":[23],"of":[24,30,55,86,98,110,147,154,163],"spectrograms":[26],"to":[27,36,50,77,174],"series":[29],"micro":[31],"action":[33,73],"unit":[34,113],"intensities":[35],"drive":[37],"blendshape":[40],"face":[41],"model.":[42],"In":[43],"particular,":[44],"our":[45,66,164,168],"model":[47,67,170],"is":[48,171],"able":[49],"learn":[51],"the":[52,63,84,99,121],"latent":[53],"representations":[54],"time-varying":[56],"contextual":[57],"information":[58],"and":[59,101,157,180],"affective":[60,105],"states":[61,106,159],"within":[62],"speech.":[64],"Hence,":[65],"not":[68],"only":[69],"activates":[70],"appropriate":[71],"units":[74,130],"at":[75],"inference":[76],"depict":[78],"different":[79,148],"utterance":[80],"generating":[81],"actions,":[82],"in":[83,117,138,177],"form":[85],"lip":[87],"movements,":[88],"but":[89],"also,":[90],"without":[91],"any":[92],"assumption,":[93],"automatically":[94],"estimates":[95],"emotional":[96,158],"intensity":[97],"speaker":[100],"reproduces":[102],"her":[103],"ever-changing":[104],"by":[107],"adjusting":[108],"strength":[109],"related":[111],"activations.":[114],"For":[115],"example,":[116],"happy":[119],"speech,":[120],"mouth":[122],"opens":[123],"wider":[124],"than":[125],"normal,":[126],"while":[127],"other":[128],"are":[131],"relaxed;":[132],"or":[133],"both":[134],"eyebrows":[135],"raise":[136],"higher":[137],"surprised":[140],"state.":[141],"Experiments":[142],"on":[143],"diverse":[144],"audiovisual":[145],"corpora":[146],"actors":[149],"across":[150],"wide":[152],"range":[153],"actions":[156],"show":[160],"promising":[161],"results":[162],"approach.":[165],"Being":[166],"speaker-independent,":[167],"generalized":[169],"readily":[172],"applicable":[173],"various":[175],"tasks":[176],"human-machine":[178],"interaction":[179],"animation.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}