{"id":"https://openalex.org/W4403780616","doi":"https://doi.org/10.1145/3664647.3681366","title":"MMHead: Towards Fine-grained Multi-modal 3D Facial Animation","display_name":"MMHead: Towards Fine-grained Multi-modal 3D Facial Animation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780616","doi":"https://doi.org/10.1145/3664647.3681366"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102595968","display_name":"Sijing Wu","orcid":"https://orcid.org/0009-0000-7753-1596"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijing Wu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-7753-1596","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778543","display_name":"Yunhao Li","orcid":"https://orcid.org/0000-0002-7337-1748"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhao Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7337-1748","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048907728","display_name":"Yichao Yan","orcid":"https://orcid.org/0000-0003-3209-8965"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichao Yan","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3209-8965","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015291775","display_name":"Huiyu Duan","orcid":"https://orcid.org/0000-0002-6519-4067"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyu Duan","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6519-4067","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406050","display_name":"Ziwei Liu","orcid":"https://orcid.org/0000-0002-4220-5958"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziwei Liu","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4220-5958","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8165-9322","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7966","last_page":"7975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9954000115394592,"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":0.9890999794006348,"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-science","display_name":"Computer science","score":0.7638737559318542},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6770967245101929},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5324975252151489},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.47159895300865173},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4627974033355713},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3968830704689026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3343132734298706},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08462744951248169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638737559318542},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6770967245101929},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5324975252151489},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.47159895300865173},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4627974033355713},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3968830704689026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3343132734298706},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08462744951248169},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W1990883837","https://openalex.org/W2051297709","https://openalex.org/W2154961933","https://openalex.org/W2163131540","https://openalex.org/W2194775991","https://openalex.org/W2468212864","https://openalex.org/W2470957930","https://openalex.org/W2604379605","https://openalex.org/W2769666294","https://openalex.org/W2799185473","https://openalex.org/W2803193013","https://openalex.org/W2883221003","https://openalex.org/W2914165399","https://openalex.org/W2981263323","https://openalex.org/W3096831136","https://openalex.org/W3099284785","https://openalex.org/W3154411171","https://openalex.org/W3174194560","https://openalex.org/W3180355996","https://openalex.org/W3180794345","https://openalex.org/W4200630629","https://openalex.org/W4212774754","https://openalex.org/W4220774645","https://openalex.org/W4288043288","https://openalex.org/W4288079574","https://openalex.org/W4310380119","https://openalex.org/W4312635677","https://openalex.org/W4312722235","https://openalex.org/W4312933868","https://openalex.org/W4312936899","https://openalex.org/W4313145975","https://openalex.org/W4385825592","https://openalex.org/W4386065848","https://openalex.org/W4386066305","https://openalex.org/W4386071464","https://openalex.org/W4386076250","https://openalex.org/W4386076458","https://openalex.org/W4387963302","https://openalex.org/W4387967971","https://openalex.org/W4387969119","https://openalex.org/W4387969168","https://openalex.org/W4388157164","https://openalex.org/W4388186306","https://openalex.org/W4390872742","https://openalex.org/W4390872926","https://openalex.org/W4390873123","https://openalex.org/W4391305822","https://openalex.org/W4393153464","https://openalex.org/W4402660084"],"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/W2215755978"],"abstract_inverted_index":{"3D":[0,17,29,34,46,60,71,128,162,192,222],"facial":[1,18,30,35,47,61,72,92,129,168,193,223],"animation":[2,19,36,48,62,165],"has":[3,20],"attracted":[4],"considerable":[5],"attention":[6],"due":[7,40],"to":[8,41,125,182],"its":[9],"extensive":[10],"applications":[11],"in":[12,216],"the":[13,42,142,151,184,208,218],"multimedia":[14],"field.":[15],"Audio-driven":[16],"been":[21],"widely":[22],"explored":[23,39],"with":[24,141],"promising":[25],"results.":[26],"However,":[27],"multi-modal":[28,45,59,185,221],"animation,":[31],"especially":[32],"text-guided":[33],"is":[37,180],"rarely":[38],"lack":[43],"of":[44,67,70,144,211,220],"dataset.":[49],"To":[50],"fill":[51],"this":[52],"gap,":[53],"we":[54,112,154],"first":[55],"construct":[56],"a":[57,172],"large-scale":[58],"dataset,":[63,153],"MMHead,":[64],"which":[65,195],"consists":[66],"49":[68],"hours":[69],"motion":[73,130,169],"sequences,":[74],"speech":[75],"audios,":[76],"and":[77,88,93,98,102,120,135,147,166,187,190,204,214],"rich":[78],"hierarchical":[79,138],"text":[80,83,139],"annotations.":[81],"Each":[82],"annotation":[84],"contains":[85],"abstract":[86],"action":[87],"emotion":[89],"descriptions,":[90,101],"fine-grained":[91],"head":[94,99,164],"movements":[95],"(i.e.,":[96],"expression":[97],"pose)":[100],"three":[103],"possible":[104],"scenarios":[105],"that":[106],"may":[107],"cause":[108],"such":[109],"emotion.":[110],"Concretely,":[111],"integrate":[113],"five":[114],"public":[115],"2D":[116],"portrait":[117],"video":[118],"datasets,":[119],"propose":[121],"an":[122],"automatic":[123],"pipeline":[124],"1)":[126],"reconstruct":[127],"sequences":[131],"from":[132],"monocular":[133],"videos;":[134],"2)":[136],"obtain":[137],"annotations":[140],"help":[143],"AU":[145],"detection":[146],"ChatGPT.":[148],"Based":[149],"on":[150,199],"MMHead":[152],"establish":[155],"benchmarks":[156,215],"for":[157],"two":[158],"new":[159],"tasks:":[160],"text-induced":[161],"talking":[163],"text-to-3D":[167],"generation.":[170],"Moreover,":[171],"simple":[173],"but":[174],"efficient":[175],"VQ-VAE-based":[176],"method":[177],"named":[178],"MM2Face":[179],"proposed":[181],"unify":[183],"information":[186],"generate":[188],"diverse":[189],"plausible":[191],"motions,":[194],"achieves":[196],"competitive":[197],"results":[198],"both":[200],"benchmarks.":[201],"Extensive":[202],"experiments":[203],"comprehensive":[205],"analysis":[206],"demonstrate":[207],"significant":[209],"potential":[210],"our":[212],"dataset":[213,226],"promoting":[217],"development":[219],"animation.":[224],"The":[225],"will":[227],"be":[228],"released":[229],"at:":[230],"https://wsj-sjtu.github.io/MMHead/.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}