{"id":"https://openalex.org/W4392903096","doi":"https://doi.org/10.1109/icassp48485.2024.10447526","title":"Enhancing Realism in 3D Facial Animation Using Conformer-Based Generation and Automated Post-Processing","display_name":"Enhancing Realism in 3D Facial Animation Using Conformer-Based Generation and Automated Post-Processing","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903096","doi":"https://doi.org/10.1109/icassp48485.2024.10447526"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103063144","display_name":"Yi Zhao","orcid":"https://orcid.org/0000-0002-3555-9408"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Zhao","raw_affiliation_strings":["Kuaishou Technology Co., Ltd,Beijing,China","Kuaishou Technology Co., Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd,Beijing,China","institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology Co., Ltd, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028353824","display_name":"Chunyu Qiang","orcid":"https://orcid.org/0009-0007-2290-3074"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Qiang","raw_affiliation_strings":["Kuaishou Technology Co., Ltd,Beijing,China","Kuaishou Technology Co., Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd,Beijing,China","institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology Co., Ltd, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348721","display_name":"Hao Li","orcid":"https://orcid.org/0009-0005-4319-9026"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]},{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["Kuaishou Technology Co., Ltd,Beijing,China","Kuaishou Technology Co., Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd,Beijing,China","institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology Co., Ltd, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100888407","display_name":"Yulan Hu","orcid":"https://orcid.org/0000-0003-1350-7305"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]},{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulan Hu","raw_affiliation_strings":["Kuaishou Technology Co., Ltd,Beijing,China","Kuaishou Technology Co., Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd,Beijing,China","institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology Co., Ltd, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032740716","display_name":"Wangjin Zhou","orcid":"https://orcid.org/0009-0007-0693-5316"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wangjin Zhou","raw_affiliation_strings":["Kyoto University,Kyoto,Japan","Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan","National Institute of Information and Communications Technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103063144"],"corresponding_institution_ids":["https://openalex.org/I4210155967","https://openalex.org/I4401726859"],"apc_list":null,"apc_paid":null,"fwci":0.2468,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46098061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"8341","last_page":"8345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9973999857902527,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9915000200271606,"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/animation","display_name":"Animation","score":0.7652599215507507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7449592351913452},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.6776008605957031},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.5903164148330688},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5840367078781128},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5675324201583862},{"id":"https://openalex.org/keywords/realism","display_name":"Realism","score":0.5669771432876587},{"id":"https://openalex.org/keywords/character-animation","display_name":"Character animation","score":0.5265533924102783},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5158273577690125},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.49787187576293945},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.46553435921669006},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.4502718150615692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43638208508491516},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4158245027065277},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38641902804374695},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3330633044242859},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.19883963465690613},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19282329082489014},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.16875672340393066},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.12120881676673889},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.11768567562103271},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1126219630241394},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.08961206674575806}],"concepts":[{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7652599215507507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449592351913452},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.6776008605957031},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.5903164148330688},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5840367078781128},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5675324201583862},{"id":"https://openalex.org/C543847140","wikidata":"https://www.wikidata.org/wiki/Q2642826","display_name":"Realism","level":2,"score":0.5669771432876587},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.5265533924102783},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5158273577690125},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49787187576293945},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.46553435921669006},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.4502718150615692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43638208508491516},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4158245027065277},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38641902804374695},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3330633044242859},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.19883963465690613},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19282329082489014},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.16875672340393066},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.12120881676673889},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.11768567562103271},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1126219630241394},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.08961206674575806},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50729888","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100931491","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1588539311","https://openalex.org/W2024465744","https://openalex.org/W2063634999","https://openalex.org/W2468212864","https://openalex.org/W2741151796","https://openalex.org/W2770121394","https://openalex.org/W2883861033","https://openalex.org/W2895226286","https://openalex.org/W2946200149","https://openalex.org/W2976925951","https://openalex.org/W2981263323","https://openalex.org/W3087837792","https://openalex.org/W3093450153","https://openalex.org/W3097777922","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3107666850","https://openalex.org/W3154411171","https://openalex.org/W3158108395","https://openalex.org/W3160694286","https://openalex.org/W3174763799","https://openalex.org/W3175779516","https://openalex.org/W3207281888","https://openalex.org/W4200630629","https://openalex.org/W4240592325","https://openalex.org/W4304087182","https://openalex.org/W4382469130","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6763832098","https://openalex.org/W6794682062"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2748502319","https://openalex.org/W4251524041","https://openalex.org/W2906438086","https://openalex.org/W3094080214","https://openalex.org/W615219140","https://openalex.org/W3088156289","https://openalex.org/W2097922480","https://openalex.org/W1521793179","https://openalex.org/W3040900128"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"has":[2],"propelled":[3],"the":[4,21,39,75,78,96],"development":[5],"of":[6,24,77,98],"realistic":[7],"talking-face":[8],"videos":[9],"for":[10],"avatars.":[11],"Yet,":[12],"animating":[13],"3D":[14],"cartoon":[15],"avatars":[16],"remains":[17],"intricate":[18],"due":[19],"to":[20,90,111],"imprecise":[22],"nature":[23],"facial-driven":[25],"data.":[26],"This":[27,88],"often":[28],"manifests":[29],"as":[30,115],"inconsistent":[31],"mouth":[32],"configurations":[33],"and":[34,61,94],"rigid":[35],"facial":[36],"expressions,":[37],"curbing":[38],"animation\u2019s":[40],"realism.":[41],"Addressing":[42],"these":[43],"issues,":[44],"we":[45,82],"introduce":[46],"a":[47,68,84],"conformer-based":[48],"framework":[49],"that":[50],"derives":[51],"expression":[52,106],"coefficients":[53],"directly":[54],"from":[55],"phonemes,":[56],"thereby":[57],"elevating":[58],"prediction":[59],"precision":[60],"minimizing":[62],"manual":[63],"oversight.":[64],"Furthermore,":[65],"by":[66,117],"harnessing":[67],"pre-trained":[69],"emotion":[70],"blending":[71],"module":[72],"coupled":[73],"with":[74],"keyframe":[76],"target":[79],"emotional":[80,92],"character,":[81],"employ":[83],"zero-shot":[85],"adaptation":[86],"technique.":[87],"serves":[89],"amplify":[91],"expressions":[93],"bolster":[95],"authenticity":[97],"lip":[99],"dynamics.":[100],"Our":[101],"methodology":[102],"adeptly":[103],"registers":[104],"nuanced":[105],"shifts":[107],"in":[108],"avatars,":[109],"leading":[110],"remarkably":[112],"lifelike":[113],"animations,":[114],"substantiated":[116],"our":[118],"experimental":[119],"findings.":[120]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
