{"id":"https://openalex.org/W2106286519","doi":"https://doi.org/10.1109/tdpvt.2002.1024147","title":"Real-time speech-driven 3D face animation","display_name":"Real-time speech-driven 3D face animation","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2106286519","doi":"https://doi.org/10.1109/tdpvt.2002.1024147","mag":"2106286519"},"language":"en","primary_location":{"id":"doi:10.1109/tdpvt.2002.1024147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tdpvt.2002.1024147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission","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/A5033168441","display_name":"Pengyu Hong","orcid":"https://orcid.org/0000-0002-3177-2754"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pengyu Hong","raw_affiliation_strings":["Coordinated Science Laboratory, University of Illinois, Urbana-Champaign, USA","[Coordinated Sci. Lab, Illinois Univ., Urbana, IL, USA]"],"affiliations":[{"raw_affiliation_string":"Coordinated Science Laboratory, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[Coordinated Sci. Lab, Illinois Univ., Urbana, IL, USA]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043926363","display_name":"Zhen Wen","orcid":"https://orcid.org/0000-0001-9780-6876"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Wen","raw_affiliation_strings":["Beckman Institute, University of Illinois, Urbana-Champaign, USA","[Beckman Institute, University of Illinois, Urbana-Champaign, USA]"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[Beckman Institute, University of Illinois, Urbana-Champaign, USA]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T.S. Huang","raw_affiliation_strings":["Beckman Institute, University of Illinois, Urbana-Champaign, USA","[Beckman Institute, University of Illinois, Urbana-Champaign, USA]"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[Beckman Institute, University of Illinois, Urbana-Champaign, USA]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061000201","display_name":"Heung\u2010Yeung Shum","orcid":"https://orcid.org/0000-0002-4684-911X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Heung-Yeung Shum","raw_affiliation_strings":["Microsoft Research Laboratory-Beijing, Beijing, China","[Microsoft Research Laboratory-Beijing, Beijing, China]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Laboratory-Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Laboratory-Beijing, Beijing, China]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033168441"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.3459,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82075201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"713","last_page":"716"},"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":0.9976999759674072,"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/T10057","display_name":"Face and Expression Recognition","score":0.9843999743461609,"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":0.8142542839050293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7105798721313477},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6481145620346069},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5954564809799194},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5529096126556396},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5474158525466919},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5280562043190002},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5273338556289673},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5248434543609619},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4560506343841553},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45317959785461426},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.393172949552536},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.11162072420120239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8142542839050293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7105798721313477},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6481145620346069},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5954564809799194},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5529096126556396},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5474158525466919},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5280562043190002},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5273338556289673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5248434543609619},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4560506343841553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45317959785461426},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.393172949552536},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.11162072420120239},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tdpvt.2002.1024147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tdpvt.2002.1024147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.3807","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.3807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://combio.cs.brandeis.edu/hong/Research/e_paper/3DPVT_2002/3DPVT_2002.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-161266","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-161266","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1504187604","https://openalex.org/W1547376871","https://openalex.org/W1560013842","https://openalex.org/W1581774439","https://openalex.org/W1588539311","https://openalex.org/W1857745579","https://openalex.org/W1979739996","https://openalex.org/W1992706276","https://openalex.org/W2002591263","https://openalex.org/W2013806171","https://openalex.org/W2038952578","https://openalex.org/W2082942761","https://openalex.org/W2112776351","https://openalex.org/W2115276447","https://openalex.org/W2119693577","https://openalex.org/W2125838338","https://openalex.org/W2129774149","https://openalex.org/W2133067194","https://openalex.org/W2133228161","https://openalex.org/W2139526018","https://openalex.org/W2140565496","https://openalex.org/W2147885303","https://openalex.org/W2148694408","https://openalex.org/W2152826865","https://openalex.org/W2155658135","https://openalex.org/W2172803778","https://openalex.org/W2236592196","https://openalex.org/W2295661697","https://openalex.org/W2296297070","https://openalex.org/W4231537718","https://openalex.org/W4239071497","https://openalex.org/W4292023222","https://openalex.org/W6630153011","https://openalex.org/W6632696956","https://openalex.org/W6679669933","https://openalex.org/W6682634897"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2535923857","https://openalex.org/W2989004599","https://openalex.org/W1976926596","https://openalex.org/W3094080214","https://openalex.org/W2156310872","https://openalex.org/W2356609371","https://openalex.org/W2532377291"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,147],"present":[4],"an":[5],"approach":[6],"for":[7,173],"real-time":[8,95],"speech-driven":[9],"3D":[10,20,39,44],"face":[11,174],"animation":[12],"using":[13,107],"neural":[14,105,126,160],"networks.":[15],"We":[16],"first":[17,148],"analyze":[18],"a":[19,25,30,51,77,102,142],"facial":[21,35,45,69,72],"movement":[22,73],"sequence":[23,74],"of":[24,33,54,67,89,104,153,182],"talking":[26],"subject":[27],"and":[28,85,156],"learn":[29],"quantitative":[31,177],"representation":[32],"the":[34,38,55,59,64,68,86,108,122,134,138,154,158,164,180,183],"deformations,":[36],"called":[37],"motion":[40],"units":[41],"(MUs).":[42],"A":[43,94],"deformation":[46],"can":[47],"be":[48],"approximated":[49],"by":[50,58,100],"linear":[52],"combination":[53],"MUs":[56],"weighted":[57],"MU":[60],"parameters":[61],"(MUPs)":[62],"-":[63],"visual":[65],"features":[66,88,114,136],"deformation.":[70],"The":[71,80,112,176],"synchronizes":[75],"with":[76],"audio":[78,81,87,123,135,144,165],"track.":[79],"track":[82],"is":[83,98,128],"digitized":[84],"each":[90],"frame":[91],"are":[92,115,171],"calculated.":[93],"audio-to-MUP":[96],"mapping":[97],"constructed":[99],"training":[101],"set":[103],"networks":[106],"calculated":[109],"audio-visual":[110,113],"features.":[111,124],"divided":[116],"into":[117,151],"several":[118],"groups":[119,155],"based":[120],"on":[121],"One":[125],"network":[127,161],"trained":[129],"per":[130],"group":[131],"to":[132,137,162,168],"map":[133,163],"corresponding":[139,159],"MUPs.":[140],"Given":[141],"new":[143],"feature":[145,166],"vector,":[146],"classify":[149],"it":[150],"one":[152],"select":[157],"vector":[167],"MUPs,":[169],"which":[170],"used":[172],"animation.":[175],"evaluation":[178],"shows":[179],"effectiveness":[181],"proposed":[184],"approach.":[185]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}