{"id":"https://openalex.org/W7166676886","doi":"https://doi.org/10.1145/3811818","title":"Speech-Driven 3D Facial Animation with Natural Head Movements","display_name":"Speech-Driven 3D Facial Animation with Natural Head Movements","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7166676886","doi":"https://doi.org/10.1145/3811818"},"language":"en","primary_location":{"id":"doi:10.1145/3811818","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811818","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3811818","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102641633","display_name":"Kuiyuan Sun","orcid":"https://orcid.org/0009-0007-0077-7388"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuiyuan Sun","raw_affiliation_strings":["Institute of Information Science, Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0077-7388","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026393492","display_name":"Jichao Zhang","orcid":"https://orcid.org/0000-0001-6189-9521"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jichao Zhang","raw_affiliation_strings":["School of Computer Science, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-6189-9521","affiliations":[{"raw_affiliation_string":"School of Computer Science, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392006","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-5477-1017"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Institute of Information Science, Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5477-1017","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362745","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0002-8581-9554"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Institute of Information Science, Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8581-9554","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027171279","display_name":"Nicu Sebe","orcid":"https://orcid.org/0000-0002-6597-7248"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicu Sebe","raw_affiliation_strings":["Department of Information and Computer Science, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6597-7248","affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83639786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"7","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9606999754905701,"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":0.9606999754905701,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.007000000216066837,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.007000000216066837,"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/animation","display_name":"Animation","score":0.758899986743927},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.607699990272522},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6044999957084656},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6029999852180481},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.6008999943733215},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.5306000113487244},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.5162000060081482},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43950000405311584},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4187999963760376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8622999787330627},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.758899986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593999862670898},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6581000089645386},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.607699990272522},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6044999957084656},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6029999852180481},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.6008999943733215},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.5306000113487244},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.5162000060081482},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43950000405311584},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C44710944","wikidata":"https://www.wikidata.org/wiki/Q1813564","display_name":"Skeletal animation","level":5,"score":0.3598000109195709},{"id":"https://openalex.org/C60851780","wikidata":"https://www.wikidata.org/wiki/Q17056736","display_name":"Interactive skeleton-driven simulation","level":5,"score":0.33809998631477356},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.2847999930381775},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.2624000012874603},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3811818","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811818","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:iris.unitn.it:11572/495170","is_oa":false,"landing_page_url":"https://hdl.handle.net/11572/495170","pdf_url":null,"source":{"id":"https://openalex.org/S4377196320","display_name":"Iris (University of Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3811818","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811818","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.45319193601608276,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G6272256563","display_name":null,"funder_award_id":"2021ZD0112100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7784432583","display_name":null,"funder_award_id":"2022XKRC015","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2339620988","https://openalex.org/W2753069234","https://openalex.org/W2769666294","https://openalex.org/W2803193013","https://openalex.org/W2981087920","https://openalex.org/W2981263323","https://openalex.org/W3022900894","https://openalex.org/W3109585842","https://openalex.org/W3154411171","https://openalex.org/W3171884590","https://openalex.org/W3177150198","https://openalex.org/W3177318507","https://openalex.org/W3180794345","https://openalex.org/W4200630629","https://openalex.org/W4205885905","https://openalex.org/W4290945834","https://openalex.org/W4312590328","https://openalex.org/W4312933868","https://openalex.org/W4372283500","https://openalex.org/W4382119042","https://openalex.org/W4386072021","https://openalex.org/W4386075823","https://openalex.org/W4386076108","https://openalex.org/W4386076250","https://openalex.org/W4386076301","https://openalex.org/W4386717557","https://openalex.org/W4388157164","https://openalex.org/W4390872742","https://openalex.org/W4390873123","https://openalex.org/W4402660084","https://openalex.org/W4402727930","https://openalex.org/W4402753521"],"related_works":[],"abstract_inverted_index":{"Speech-driven":[0],"3D":[1,49,83],"facial":[2,50,183,242],"animation":[3,51,137,184],"has":[4],"been":[5],"studied":[6],"for":[7,72,191],"a":[8,38,93,153,159,197,223,247],"long":[9],"time,":[10],"yet":[11],"many":[12],"challenges":[13],"still":[14],"prevent":[15],"achieving":[16],"truly":[17],"natural":[18,261],"results.":[19],"One":[20],"major":[21],"issue":[22],"is":[23,151],"that":[24,129,144,181,228,252],"current":[25],"methods":[26,185,257],"often":[27],"overlook":[28],"head":[29,54,84,94,112,127,133,146,165,171,262],"motion":[30,55,85,95,105,147,166],"during":[31],"speech.":[32],"To":[33,87,217],"address":[34],"this,":[35],"we":[36,91,157,221],"conducted":[37],"preliminary":[39],"investigation":[40],"and":[41,56,67,76,102,140,240,246,258],"identified":[42],"several":[43],"key":[44],"obstacles:":[45],"the":[46,57,103,108,136,145,164,174,192,202,210,235],"scarcity":[47],"of":[48,59,107,209,237],"datasets":[52],"with":[53,81],"limitations":[58],"regular":[60],"sequence":[61],"prediction":[62,96,167],"models":[63],"(e.g.,":[64],"Transformer,":[65],"LSTM,":[66],"GRU),":[68],"which":[69],"are":[70],"designed":[71],"discrete":[73],"dynamic":[74,123],"sequences":[75],"do":[77],"not":[78,152],"align":[79],"well":[80],"continuous":[82,122],"sequences.":[86],"solve":[88,218],"these":[89],"issues,":[90],"propose":[92,222],"module.":[97],"This":[98,205],"module":[99,161,168,227],"uses":[100,229],"audio":[101,150,176],"initial":[104],"state":[106],"mesh":[109,225],"to":[110,120,162,200,232],"predict":[111],"motion.":[113,263],"By":[114],"employing":[115],"ordinary":[116],"differential":[117],"equations":[118],"(ODE)":[119],"model":[121,199],"sequences,":[124],"it":[125],"predicts":[126],"movements":[128],"closely":[130],"resemble":[131],"real":[132],"motion,":[134],"making":[135],"more":[138],"realistic":[139],"natural.":[141],"Additionally,":[142],"recognizing":[143],"generation":[148,226],"given":[149,173],"one-to-one":[154],"mapping":[155],"problem,":[156,220],"introduce":[158],"noise":[160],"help":[163],"generate":[169,201,234],"varied":[170],"motions":[172],"same":[175],"input.":[177],"We":[178],"also":[179],"observed":[180],"previous":[182],"primarily":[186],"focus":[187],"on":[188,214],"generating":[189],"vertices":[190],"mouth":[193,238],"region":[194,239],"but":[195],"use":[196],"single":[198],"entire":[203],"face.":[204],"approach":[206,254],"wastes":[207],"some":[208],"model\u2019s":[211],"fitting":[212],"capacity":[213],"other":[215,241],"regions.":[216,243],"this":[219],"cascaded":[224],"two":[230],"modules":[231],"separately":[233],"vertex":[236],"Extensive":[244],"experiments":[245],"perceptual":[248],"user":[249],"study":[250],"show":[251],"our":[253],"outperforms":[255],"existing":[256],"produces":[259],"relatively":[260]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2026-07-01T00:00:00"}
