{"id":"https://openalex.org/W4387969119","doi":"https://doi.org/10.1145/3581783.3611775","title":"Speech-Driven 3D Face Animation with Composite and Regional Facial Movements","display_name":"Speech-Driven 3D Face Animation with Composite and Regional Facial Movements","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969119","doi":"https://doi.org/10.1145/3581783.3611775"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611775","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611775","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611775","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611775","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017383334","display_name":"Haozhe Wu","orcid":"https://orcid.org/0000-0002-3036-6930"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhe Wu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3036-6930","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026277472","display_name":"Songtao Zhou","orcid":"https://orcid.org/0009-0008-5972-3955"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songtao Zhou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-5972-3955","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039477812","display_name":"Jia Jia","orcid":"https://orcid.org/0009-0005-8449-278X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Tsinghua University & BNRist, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-8449-278X","affiliations":[{"raw_affiliation_string":"Tsinghua University & BNRist, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076090670","display_name":"Junliang Xing","orcid":"https://orcid.org/0000-0001-6801-0510"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junliang Xing","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6801-0510","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101423828","display_name":"Qi Wen","orcid":"https://orcid.org/0009-0004-8434-2071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Wen","raw_affiliation_strings":["ByteDance, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-8434-2071","affiliations":[{"raw_affiliation_string":"ByteDance, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100700272","display_name":"Xiang Wen","orcid":"https://orcid.org/0000-0001-6681-1584"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Wen","raw_affiliation_strings":["ByteDance, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6681-1584","affiliations":[{"raw_affiliation_string":"ByteDance, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6822","last_page":"6830"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9866999983787537,"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":0.9853000044822693,"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":0.740166425704956},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6956019997596741},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6622990369796753},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.6155810952186584},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5377386212348938},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5181578397750854},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4768977165222168},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4430030882358551},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.4333626627922058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34445273876190186},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2822502851486206},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.13994309306144714},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.11027726531028748},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10254830121994019},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07211422920227051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.740166425704956},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6956019997596741},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6622990369796753},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.6155810952186584},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5377386212348938},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5181578397750854},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4768977165222168},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4430030882358551},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.4333626627922058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34445273876190186},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2822502851486206},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.13994309306144714},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.11027726531028748},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10254830121994019},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07211422920227051},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611775","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611775","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611775","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:10.1145/3581783.3611775","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611775","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611775","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4257201797","display_name":null,"funder_award_id":"62222606","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5381013183","display_name":null,"funder_award_id":"61831022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G998127002","display_name":null,"funder_award_id":"62076238","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969119.pdf","grobid_xml":"https://content.openalex.org/works/W4387969119.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W219197677","https://openalex.org/W1569907127","https://openalex.org/W1990883837","https://openalex.org/W2135046866","https://openalex.org/W2154961933","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2338517121","https://openalex.org/W2468212864","https://openalex.org/W2603777577","https://openalex.org/W2739192055","https://openalex.org/W2769666294","https://openalex.org/W2804619907","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2979894294","https://openalex.org/W2981263323","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3101631197","https://openalex.org/W3154411171","https://openalex.org/W3174763799","https://openalex.org/W3209059054","https://openalex.org/W4200630629","https://openalex.org/W4281730245","https://openalex.org/W4297793551","https://openalex.org/W4304087182","https://openalex.org/W4385245566","https://openalex.org/W4386076250","https://openalex.org/W6739901393"],"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":{"Speech-driven":[0],"3D":[1,36,146,158],"face":[2,37],"animation":[3],"poses":[4],"significant":[5],"challenges":[6],"due":[7],"to":[8,43,61,85,109,157],"the":[9,21,26,53,57,62,78,95,123,133,141],"intricacy":[10],"and":[11,28,168,174,187],"variability":[12],"inherent":[13],"in":[14,34],"human":[15],"facial":[16,32,50,65,107,113,134,159,166],"movements.":[17],"This":[18],"paper":[19],"emphasizes":[20],"importance":[22],"of":[23,31,132,145,165],"considering":[24],"both":[25,87,185],"composite":[27,40,96],"regional":[29,58,124],"natures":[30,88],"movements":[33,51,66,108,114,144,167],"speech-driven":[35,49,112],"animation.":[38,92],"The":[39],"nature":[41,59],"pertains":[42],"how":[44],"speech-independent":[45],"factors":[46],"globally":[47,69],"modulate":[48],"along":[52,77],"temporal":[54],"dimension.":[55,80],"Meanwhile,":[56],"alludes":[60],"notion":[63],"that":[64,104,129,178],"are":[67,72],"not":[68],"correlated":[70],"but":[71],"actuated":[73],"by":[74],"local":[75,142],"musculature":[76],"spatial":[79,143],"It":[81],"is":[82],"thus":[83],"indispensable":[84],"incorporate":[86],"for":[89,136,154],"engendering":[90],"vivid":[91],"To":[93,121],"address":[94],"nature,":[97,125],"we":[98,149],"introduce":[99],"an":[100],"adaptive":[101],"modulation":[102],"module":[103],"employs":[105],"arbitrary":[106],"dynamically":[110],"adjust":[111],"across":[115],"frames":[116],"on":[117,140],"a":[118,151],"global":[119],"scale.":[120],"accommodate":[122],"our":[126,179],"approach":[127],"ensures":[128],"each":[130],"constituent":[131],"features":[135],"every":[137],"frame":[138],"focuses":[139],"faces.":[147],"Moreover,":[148],"present":[150],"non-autoregressive":[152],"backbone":[153],"translating":[155],"audio":[156],"movements,":[160],"which":[161],"maintains":[162],"high-frequency":[163],"nuances":[164],"facilitates":[169],"efficient":[170],"inference.":[171],"Comprehensive":[172],"experiments":[173],"user":[175],"studies":[176],"demonstrate":[177],"method":[180],"surpasses":[181],"contemporary":[182],"state-of-the-art":[183],"approaches":[184],"qualitatively":[186],"quantitatively.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}