{"id":"https://openalex.org/W4403791206","doi":"https://doi.org/10.1145/3664647.3681198","title":"AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding","display_name":"AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791206","doi":"https://doi.org/10.1145/3664647.3681198"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681198","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":"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/A5039071207","display_name":"Tao Liu","orcid":"https://orcid.org/0000-0003-4169-4160"},"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":"Tao Liu","raw_affiliation_strings":["X-LANCE Lab, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4169-4160","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104296705","display_name":"Feilong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feilong Chen","raw_affiliation_strings":["AISpeech Ltd, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-7162-8379","affiliations":[{"raw_affiliation_string":"AISpeech Ltd, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100892386","display_name":"Shuai Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Fan","raw_affiliation_strings":["AISpeech Ltd, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-0260-6080","affiliations":[{"raw_affiliation_string":"AISpeech Ltd, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035532752","display_name":"Chenpeng Du","orcid":"https://orcid.org/0000-0001-5329-0847"},"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":"Chenpeng Du","raw_affiliation_strings":["X-LANCE Lab, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5329-0847","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325612","display_name":"Qi Chen","orcid":"https://orcid.org/0000-0001-8606-8273"},"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":"Qi Chen","raw_affiliation_strings":["X-LANCE Lab, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8606-8273","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"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":"Xie Chen","raw_affiliation_strings":["X-LANCE Lab, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7423-617X","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"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":"Kai Yu","raw_affiliation_strings":["X-LANCE Lab, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7102-9826","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4997,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.9407337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6696","last_page":"6705"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9925000071525574,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9872000217437744,"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/encoding","display_name":"Encoding (memory)","score":0.6532273888587952},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5386561751365662},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5011196136474609},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4813714623451233},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.45862311124801636},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.44152742624282837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3712655305862427},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.36333778500556946},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.3008059859275818},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.16052675247192383},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12358996272087097},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.051277995109558105}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6532273888587952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5386561751365662},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5011196136474609},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4813714623451233},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.45862311124801636},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.44152742624282837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3712655305862427},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36333778500556946},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.3008059859275818},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.16052675247192383},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12358996272087097},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.051277995109558105}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681198","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":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2133665775","https://openalex.org/W2144499799","https://openalex.org/W2332267591","https://openalex.org/W2565639579","https://openalex.org/W2593463961","https://openalex.org/W2604379605","https://openalex.org/W2626914210","https://openalex.org/W2784163702","https://openalex.org/W2884460600","https://openalex.org/W2894176037","https://openalex.org/W2962785568","https://openalex.org/W2964110616","https://openalex.org/W2969985801","https://openalex.org/W3010526057","https://openalex.org/W3019952993","https://openalex.org/W3024869864","https://openalex.org/W3103152812","https://openalex.org/W3112871073","https://openalex.org/W3180770160","https://openalex.org/W3180794345","https://openalex.org/W3186090335","https://openalex.org/W3187364420","https://openalex.org/W3197199219","https://openalex.org/W4200630629","https://openalex.org/W4280631290","https://openalex.org/W4312933868","https://openalex.org/W4372262450","https://openalex.org/W4385682917","https://openalex.org/W4385801140","https://openalex.org/W4386066256","https://openalex.org/W4386066404","https://openalex.org/W4386072021","https://openalex.org/W4386075487","https://openalex.org/W4386075576","https://openalex.org/W4389115772","https://openalex.org/W4390872742","https://openalex.org/W4390872769","https://openalex.org/W4391072501","https://openalex.org/W4393147067","https://openalex.org/W4394597155","https://openalex.org/W4394597549","https://openalex.org/W4403081627","https://openalex.org/W6703049012"],"related_works":["https://openalex.org/W4235381733","https://openalex.org/W2355022049","https://openalex.org/W2060429446","https://openalex.org/W2741782512","https://openalex.org/W3011302839","https://openalex.org/W2392958391","https://openalex.org/W3155227409","https://openalex.org/W2898682874","https://openalex.org/W2386709048","https://openalex.org/W1521055772"],"abstract_inverted_index":{"The":[0],"paper":[1],"introduces":[2],"AniTalker,":[3],"an":[4,98],"innovative":[5,50],"framework":[6],"designed":[7],"to":[8,32,89,164],"generate":[9],"lifelike":[10],"talking":[11],"faces":[12],"from":[13,82],"a":[14,45,54,140,144],"single":[15],"portrait.":[16],"Unlike":[17],"existing":[18],"models":[19],"that":[20,118],"primarily":[21],"focus":[22],"on":[23],"verbal":[24],"cues":[25],"such":[26],"as":[27],"lip":[28],"synchronization":[29],"and":[30,40,63,94,112,124,153,167],"fail":[31],"capture":[33],"the":[34,75,86,95,110,119,131,137,149],"complex":[35],"dynamics":[36],"of":[37,57,126,139,151],"facial":[38,58,155,169],"expressions":[39,62],"nonverbal":[41],"cues,":[42],"AniTalker":[43,66],"employs":[44],"universal":[46],"motion":[47,68,92,113,120],"representation.":[48],"This":[49,115,157],"representation":[51,121],"effectively":[52],"captures":[53],"wide":[55],"range":[56],"dynamics,":[59],"including":[60],"subtle":[61,91],"head":[64],"movements.":[65],"enhances":[67],"depiction":[69],"through":[70],"two":[71],"self-supervised":[72],"learning":[73,103],"strategies:":[74],"first":[76],"involves":[77],"reconstructing":[78],"target":[79],"video":[80],"frames":[81,84],"source":[83],"within":[85],"same":[87],"identity":[88,99,111],"learn":[90],"representations,":[93],"second":[96],"develops":[97],"encoder":[100],"using":[101],"metric":[102],"while":[104],"actively":[105],"minimizing":[106],"mutual":[107],"information":[108],"between":[109],"encoders.":[114],"approach":[116],"ensures":[117],"is":[122],"dynamic":[123,178],"devoid":[125],"identity-specific":[127],"details,":[128],"significantly":[129],"reducing":[130],"need":[132],"for":[133,148,180],"labeled":[134],"data.":[135],"Additionally,":[136],"integration":[138],"diffusion":[141],"model":[142],"with":[143],"variance":[145],"adapter":[146],"allows":[147],"generation":[150],"diverse":[152],"controllable":[154],"animations.":[156],"method":[158],"not":[159],"only":[160],"demonstrates":[161],"AniTalker's":[162],"capability":[163],"create":[165],"detailed":[166],"realistic":[168],"movements":[170],"but":[171],"also":[172],"underscores":[173],"its":[174],"potential":[175],"in":[176],"crafting":[177],"avatars":[179],"real-world":[181],"applications.":[182],"Synthetic":[183],"results":[184],"can":[185],"be":[186],"viewed":[187],"at":[188],"https://github.com/X-LANCE/AniTalker.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
