{"id":"https://openalex.org/W4400582137","doi":"https://doi.org/10.1145/3641519.3657413","title":"Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance","display_name":"Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400582137","doi":"https://doi.org/10.1145/3641519.3657413"},"language":"en","primary_location":{"id":"doi:10.1145/3641519.3657413","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3641519.3657413","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3641519.3657413","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104306964","display_name":"Qingcheng Zhao","orcid":"https://orcid.org/0009-0002-8968-8341"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingcheng Zhao","raw_affiliation_strings":["ShanghaiTech University, China and Deemos Technology, China"],"raw_orcid":"https://orcid.org/0009-0002-8968-8341","affiliations":[{"raw_affiliation_string":"ShanghaiTech University, China and Deemos Technology, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062667045","display_name":"P. E. Long","orcid":"https://orcid.org/0009-0002-8490-2652"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyu Long","raw_affiliation_strings":["ShanghaiTech University, China and Deemos Technology, China"],"raw_orcid":"https://orcid.org/0009-0002-8490-2652","affiliations":[{"raw_affiliation_string":"ShanghaiTech University, China and Deemos Technology, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038142929","display_name":"Qixuan Zhang","orcid":"https://orcid.org/0000-0002-4837-7152"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixuan Zhang","raw_affiliation_strings":["ShanghaiTech University, China and Deemos Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-4837-7152","affiliations":[{"raw_affiliation_string":"ShanghaiTech University, China and Deemos Technology, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037765030","display_name":"Dafei Qin","orcid":"https://orcid.org/0009-0001-4992-4760"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dafei Qin","raw_affiliation_strings":["University of Hong Kong, China and Deemos Technology, China"],"raw_orcid":"https://orcid.org/0009-0001-4992-4760","affiliations":[{"raw_affiliation_string":"University of Hong Kong, China and Deemos Technology, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104174884","display_name":"Han Liang","orcid":"https://orcid.org/0009-0008-2444-9685"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Liang","raw_affiliation_strings":["ShanghaiTech University, China"],"raw_orcid":"https://orcid.org/0009-0008-2444-9685","affiliations":[{"raw_affiliation_string":"ShanghaiTech University, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044492786","display_name":"Longwen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longwen Zhang","raw_affiliation_strings":["ShanghaiTech University, China and Deemos Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-8508-3359","affiliations":[{"raw_affiliation_string":"ShanghaiTech University, China and Deemos Technology, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001933895","display_name":"Yingliang Zhang","orcid":"https://orcid.org/0000-0002-0594-7549"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingliang Zhang","raw_affiliation_strings":["DGene Digital Technology Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0002-0594-7549","affiliations":[{"raw_affiliation_string":"DGene Digital Technology Co., Ltd., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101500646","display_name":"Jingyi Yu","orcid":"https://orcid.org/0000-0001-9198-6853"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Yu","raw_affiliation_strings":["ShanghaiTech University, China"],"raw_orcid":"https://orcid.org/0000-0001-9198-6853","affiliations":[{"raw_affiliation_string":"ShanghaiTech University, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100777698","display_name":"Lan Xu","orcid":"https://orcid.org/0000-0002-8807-7787"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan Xu","raw_affiliation_strings":["ShanghaiTech University, China"],"raw_orcid":"https://orcid.org/0000-0002-8807-7787","affiliations":[{"raw_affiliation_string":"ShanghaiTech University, China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5104306964"],"corresponding_institution_ids":["https://openalex.org/I30809798"],"apc_list":null,"apc_paid":null,"fwci":7.3429,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.98046147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"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":0.9940000176429749,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9851999878883362,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8359237909317017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7405300140380859},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6220228672027588},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5172784328460693},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4669540822505951},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3195716440677643},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3183686137199402},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.19897004961967468}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8359237909317017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405300140380859},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6220228672027588},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5172784328460693},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4669540822505951},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3195716440677643},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3183686137199402},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.19897004961967468}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3641519.3657413","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3641519.3657413","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3641519.3657413","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3641519.3657413","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2064400654","https://openalex.org/W2108033344","https://openalex.org/W2153621263","https://openalex.org/W2154961933","https://openalex.org/W2165228122","https://openalex.org/W2237250383","https://openalex.org/W2277958045","https://openalex.org/W2468212864","https://openalex.org/W2470254954","https://openalex.org/W2582523095","https://openalex.org/W2737658251","https://openalex.org/W2739192055","https://openalex.org/W2751503239","https://openalex.org/W2752796333","https://openalex.org/W2769666294","https://openalex.org/W2796822548","https://openalex.org/W2803193013","https://openalex.org/W2804619907","https://openalex.org/W2889050557","https://openalex.org/W2895226286","https://openalex.org/W2897760566","https://openalex.org/W2914304175","https://openalex.org/W2963557052","https://openalex.org/W2981263323","https://openalex.org/W3008956107","https://openalex.org/W3015873132","https://openalex.org/W3034192160","https://openalex.org/W3036120140","https://openalex.org/W3097792222","https://openalex.org/W3105015787","https://openalex.org/W3108710777","https://openalex.org/W3109154889","https://openalex.org/W3135367836","https://openalex.org/W3154411171","https://openalex.org/W3180794345","https://openalex.org/W3192580080","https://openalex.org/W3197199219","https://openalex.org/W3202128205","https://openalex.org/W4200630629","https://openalex.org/W4200633626","https://openalex.org/W4309803402","https://openalex.org/W4312309978","https://openalex.org/W4312497550","https://openalex.org/W4312567281","https://openalex.org/W4312933868","https://openalex.org/W4312995056","https://openalex.org/W4328028374","https://openalex.org/W4377010269","https://openalex.org/W4380994134","https://openalex.org/W4385284180","https://openalex.org/W4385536531","https://openalex.org/W4386072021","https://openalex.org/W4386075984","https://openalex.org/W4386076250","https://openalex.org/W4386076654","https://openalex.org/W4387195417","https://openalex.org/W4387421789","https://openalex.org/W4387967971","https://openalex.org/W4388157164","https://openalex.org/W4389334989","https://openalex.org/W4390872742","https://openalex.org/W4390873054","https://openalex.org/W4390873123","https://openalex.org/W4394698479","https://openalex.org/W4400818936"],"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/W3094080214","https://openalex.org/W2535923857","https://openalex.org/W2156310872","https://openalex.org/W2356609371"],"abstract_inverted_index":{"The":[0],"synthesis":[1,153],"of":[2,16,36,91,159],"3D":[3,104,165],"facial":[4,19,60,105,127,151,166],"animations":[5],"from":[6,30,87,134],"speech":[7],"has":[8],"garnered":[9],"considerable":[10],"attention.":[11],"Due":[12],"to":[13,64,79],"the":[14,95,157],"scarcity":[15],"high-quality":[17,81],"4D":[18],"data":[20],"and":[21,33,62,73,83,101,111,137,161],"well-annotated":[22,109],"abundant":[23],"multi-modality":[24,132],"labels,":[25],"previous":[26],"methods":[27],"often":[28],"suffer":[29],"limited":[31],"realism":[32],"a":[34,44,65,88,98,118],"lack":[35],"flexible":[37],"conditioning.":[38],"We":[39,46],"address":[40],"this":[41],"challenge":[42],"through":[43],"trilogy.":[45],"first":[47],"introduce":[48],"Generalized":[49],"Neural":[50],"Parametric":[51],"Facial":[52],"Asset":[53],"(GNPFA),":[54],"an":[55],"efficient":[56],"variational":[57],"auto-encoder":[58],"mapping":[59],"geometry":[61],"images":[63],"highly":[66],"generalized":[67],"expression":[68],"latent":[69,123],"space,":[70],"decoupling":[71],"expressions":[72,82],"identities.":[74],"Then,":[75],"we":[76,115],"utilize":[77],"GNPFA":[78,122],"extract":[80],"accurate":[84],"head":[85],"poses":[86],"large":[89],"array":[90],"videos.":[92],"This":[93],"presents":[94],"M2F-D":[96],"dataset,":[97],"large,":[99],"diverse,":[100],"scan-level":[102],"co-speech":[103,126],"animation":[106,128,152],"dataset":[107],"with":[108],"emotion":[110],"style":[112,162],"labels.":[113],"Finally,":[114],"propose":[116],"Media2Face,":[117],"diffusion":[119],"model":[120,144],"in":[121,150,164],"space":[124],"for":[125],"generation,":[129],"accepting":[130],"rich":[131],"guidances":[133],"audio,":[135],"text,":[136],"image.":[138],"Extensive":[139],"experiments":[140],"demonstrate":[141],"that":[142],"our":[143],"not":[145],"only":[146],"achieves":[147],"high":[148],"fidelity":[149],"but":[154],"also":[155],"broadens":[156],"scope":[158],"expressiveness":[160],"adaptability":[163],"animation.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":5}],"updated_date":"2026-05-29T09:21:14.243279","created_date":"2025-10-10T00:00:00"}