{"id":"https://openalex.org/W4412588114","doi":"https://doi.org/10.1145/3721238.3730672","title":"Model See Model Do: Speech-Driven Facial Animation with Style Control","display_name":"Model See Model Do: Speech-Driven Facial Animation with Style Control","publication_year":2025,"publication_date":"2025-07-23","ids":{"openalex":"https://openalex.org/W4412588114","doi":"https://doi.org/10.1145/3721238.3730672"},"language":"en","primary_location":{"id":"doi:10.1145/3721238.3730672","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3721238.3730672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.01319","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101190218","display_name":"Yifang Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120918","display_name":"Dynamic Graphics (United States)","ror":"https://ror.org/02wxws056","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120918"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yifang Pan","raw_affiliation_strings":["Department of Computer Science, Dynamic Graphics Project, University of Toronto, North York, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5194-0359","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Dynamic Graphics Project, University of Toronto, North York, Ontario, Canada","institution_ids":["https://openalex.org/I4210120918"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102945957","display_name":"Karan Singh","orcid":"https://orcid.org/0000-0002-2232-7480"},"institutions":[{"id":"https://openalex.org/I4210120918","display_name":"Dynamic Graphics (United States)","ror":"https://ror.org/02wxws056","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120918"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karan Singh","raw_affiliation_strings":["Department of Computer Science, Dynamic Graphics Project, University of Toronto, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2232-7480","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Dynamic Graphics Project, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I4210120918"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025564604","display_name":"Luiz G. Hafemann","orcid":"https://orcid.org/0000-0002-8311-0728"},"institutions":[{"id":"https://openalex.org/I4210104072","display_name":"Ubisoft (Canada)","ror":"https://ror.org/01hmp5p66","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210104072"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Luiz Gustavo Hafemann","raw_affiliation_strings":["La Forge, Ubisoft, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8311-0728","affiliations":[{"raw_affiliation_string":"La Forge, Ubisoft, Montreal, Canada","institution_ids":["https://openalex.org/I4210104072"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101190218"],"corresponding_institution_ids":["https://openalex.org/I4210120918"],"apc_list":null,"apc_paid":null,"fwci":0.9814,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77792397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9973999857902527,"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":0.9648000001907349,"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-facial-animation","display_name":"Computer facial animation","score":0.7884982824325562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7534815669059753},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6665061116218567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6039333939552307},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5666223764419556},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5115214586257935},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.4845265746116638},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42442992329597473},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3775980770587921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.363229900598526},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.21693775057792664},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.14826777577400208},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.07194742560386658}],"concepts":[{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.7884982824325562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534815669059753},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6665061116218567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6039333939552307},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5666223764419556},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5115214586257935},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.4845265746116638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42442992329597473},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3775980770587921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.363229900598526},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.21693775057792664},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.14826777577400208},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.07194742560386658}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3721238.3730672","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3721238.3730672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.01319","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.01319","pdf_url":"https://arxiv.org/pdf/2505.01319","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.01319","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.01319","pdf_url":"https://arxiv.org/pdf/2505.01319","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1485743559","https://openalex.org/W1554803342","https://openalex.org/W2071096833","https://openalex.org/W2154961933","https://openalex.org/W2468212864","https://openalex.org/W2739192055","https://openalex.org/W2769666294","https://openalex.org/W2794490148","https://openalex.org/W2803193013","https://openalex.org/W2949836599","https://openalex.org/W3019952993","https://openalex.org/W3034192160","https://openalex.org/W3036167779","https://openalex.org/W3099284785","https://openalex.org/W3109114891","https://openalex.org/W4200526174","https://openalex.org/W4224929261","https://openalex.org/W4226281991","https://openalex.org/W4226317937","https://openalex.org/W4287119707","https://openalex.org/W4287209918","https://openalex.org/W4287556650","https://openalex.org/W4288055169","https://openalex.org/W4288099666","https://openalex.org/W4288327876","https://openalex.org/W4288358543","https://openalex.org/W4296405085","https://openalex.org/W4297841867","https://openalex.org/W4298186886","https://openalex.org/W4309873549","https://openalex.org/W4311034186","https://openalex.org/W4313483299","https://openalex.org/W4353007438","https://openalex.org/W4361193395","https://openalex.org/W4362598232","https://openalex.org/W4380994134","https://openalex.org/W4386076250","https://openalex.org/W4390046737","https://openalex.org/W4391420692","https://openalex.org/W4394906559","https://openalex.org/W4400818936","https://openalex.org/W4404987275","https://openalex.org/W4405627619"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2532377291","https://openalex.org/W1976926596","https://openalex.org/W2989004599","https://openalex.org/W2535923857","https://openalex.org/W3094080214","https://openalex.org/W2156310872","https://openalex.org/W2356609371"],"abstract_inverted_index":{"Speech-driven":[0],"3D":[1],"facial":[2,72],"animation":[3],"plays":[4],"a":[5,49,56,61,87],"key":[6,96],"role":[7],"in":[8,26,151],"applications":[9],"such":[10],"as":[11],"virtual":[12],"avatars,":[13],"gaming,":[14],"and":[15,31,41,69,101,142],"digital":[16],"content":[17],"creation.":[18],"While":[19],"existing":[20],"methods":[21],"have":[22],"made":[23],"significant":[24],"progress":[25],"achieving":[27,158],"accurate":[28],"lip":[29,114,160],"synchronization":[30,115,161],"generating":[32],"basic":[33],"emotional":[34],"expressions,":[35],"they":[36],"often":[37],"struggle":[38],"to":[39,65,81,108,122],"capture":[40,123],"effectively":[42],"transfer":[43],"nuanced":[44],"performance":[45],"styles.":[46],"We":[47],"propose":[48],"novel":[50,88],"example-based":[51],"generation":[52,106],"framework":[53],"that":[54,129],"conditions":[55],"latent":[57],"diffusion":[58,105],"model":[59,121],"on":[60],"reference":[62,100],"style":[63,83,92,111,156],"clip":[64],"produce":[66],"highly":[67],"expressive":[68],"temporally":[70],"coherent":[71],"animations.":[73],"To":[74],"address":[75],"the":[76,82,99,104,110,120,130,136,146,154],"challenge":[77],"of":[78,148],"accurately":[79],"adhering":[80],"reference,":[84],"we":[85],"introduce":[86],"conditioning":[89],"mechanism":[90],"called":[91],"basis,":[93],"which":[94],"extracts":[95],"poses":[97],"from":[98],"additively":[102],"guides":[103],"process":[107],"fit":[109],"without":[112],"compromising":[113],"quality.":[116],"This":[117],"approach":[118],"enables":[119],"subtle":[124],"stylistic":[125],"cues":[126],"while":[127,157],"ensuring":[128],"generated":[131],"animations":[132],"align":[133],"closely":[134],"with":[135],"input":[137],"speech.":[138],"Extensive":[139],"qualitative,":[140],"quantitative,":[141],"perceptual":[143],"evaluations":[144],"demonstrate":[145],"effectiveness":[147],"our":[149],"method":[150],"faithfully":[152],"reproducing":[153],"desired":[155],"superior":[159],"across":[162],"various":[163],"speech":[164],"scenarios.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-29T09:21:14.243279","created_date":"2025-10-10T00:00:00"}