{"id":"https://openalex.org/W4387682247","doi":"https://doi.org/10.1109/tip.2023.3323452","title":"Toward Fine-Grained Talking Face Generation","display_name":"Toward Fine-Grained Talking Face Generation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387682247","doi":"https://doi.org/10.1109/tip.2023.3323452","pmid":"https://pubmed.ncbi.nlm.nih.gov/37843991"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3323452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3323452","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5047740567","display_name":"Zhicheng Sheng","orcid":"https://orcid.org/0000-0002-9245-3124"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Sheng","raw_affiliation_strings":["Department of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-9245-3124","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457438","display_name":"Meng Liu","orcid":"https://orcid.org/0000-0002-1582-5764"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":["School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-1582-5764","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039731055","display_name":"Yinwei Wei","orcid":"https://orcid.org/0000-0003-1791-3159"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yinwei Wei","raw_affiliation_strings":["School of Computing, National University of Singapore, Queenstown, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-1791-3159","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048947531","display_name":"Zan Gao","orcid":"https://orcid.org/0000-0003-2182-5741"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zan Gao","raw_affiliation_strings":["Shandong Artificial Intelligence Institute, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-2182-5741","affiliations":[{"raw_affiliation_string":"Shandong Artificial Intelligence Institute, Jinan, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3191,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57620092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"5794","last_page":"5807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9939000010490417,"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":0.9939000010490417,"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":0.9861999750137329,"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":0.9646999835968018,"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":0.8074403405189514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6932862401008606},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6777475476264954},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5370449423789978},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5310642719268799},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.5306222438812256},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5246089696884155},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.506248414516449},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4535662829875946},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4347708523273468},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4207383394241333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8074403405189514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6932862401008606},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6777475476264954},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5370449423789978},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5310642719268799},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.5306222438812256},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5246089696884155},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.506248414516449},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4535662829875946},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4347708523273468},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4207383394241333},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3323452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3323452","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:37843991","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37843991","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3968320906","display_name":null,"funder_award_id":"62376140","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7231895066","display_name":null,"funder_award_id":"U1936203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7696304900","display_name":null,"funder_award_id":"62006142","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W2015143272","https://openalex.org/W2102813107","https://openalex.org/W2133665775","https://openalex.org/W2134963900","https://openalex.org/W2237250383","https://openalex.org/W2331128040","https://openalex.org/W2603777577","https://openalex.org/W2604379605","https://openalex.org/W2614580201","https://openalex.org/W2738406145","https://openalex.org/W2794490148","https://openalex.org/W2883861033","https://openalex.org/W2914217321","https://openalex.org/W2944294033","https://openalex.org/W2949662773","https://openalex.org/W2956959730","https://openalex.org/W2962785568","https://openalex.org/W2963290645","https://openalex.org/W2963419579","https://openalex.org/W2963627347","https://openalex.org/W2964559396","https://openalex.org/W2979894294","https://openalex.org/W2984700035","https://openalex.org/W2990452356","https://openalex.org/W3008823916","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3082772348","https://openalex.org/W3089177030","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3104792420","https://openalex.org/W3109114891","https://openalex.org/W3109585842","https://openalex.org/W3157506437","https://openalex.org/W3171371659","https://openalex.org/W3174865552","https://openalex.org/W3176179930","https://openalex.org/W3176368002","https://openalex.org/W3180770160","https://openalex.org/W3186090335","https://openalex.org/W3197199219","https://openalex.org/W3211147706","https://openalex.org/W4221153068","https://openalex.org/W6618372016","https://openalex.org/W6735927292","https://openalex.org/W6750489868","https://openalex.org/W6767264202","https://openalex.org/W6783376789","https://openalex.org/W6795140394","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W1827696521","https://openalex.org/W2101105382","https://openalex.org/W2039848376","https://openalex.org/W2173450654","https://openalex.org/W2621720158","https://openalex.org/W2130272765","https://openalex.org/W2091722187","https://openalex.org/W2006196742","https://openalex.org/W2055991023","https://openalex.org/W2089042722"],"abstract_inverted_index":{"Talking":[0],"face":[1],"generation":[2],"is":[3,26,221],"the":[4,51,54,93,114,118,133,141,152,172,194,205,208,229,233],"process":[5],"of":[6,53,89,135,211,232],"synthesizing":[7],"a":[8,13,22,82,98,123,161,177,199,215,224],"lip-synchronized":[9],"video":[10,25],"when":[11],"given":[12],"reference":[14,55],"portrait":[15],"and":[16,48,107,154,238],"an":[17,184],"audio":[18],"clip.":[19],"However,":[20],"generating":[21],"fine-grained":[23],"talking":[24,201],"nontrivial":[27],"due":[28],"to":[29,101,127,145,159],"several":[30,255],"challenges:":[31],"1)":[32],"capturing":[33],"vivid":[34],"facial":[35,73,104,149,212],"expressions,":[36],"such":[37],"as":[38,113],"muscle":[39,74],"movements;":[40],"2)":[41],"ensuring":[42],"smooth":[43,147,169],"transitions":[44],"between":[45],"consecutive":[46],"frames;":[47],"3)":[49],"preserving":[50],"details":[52],"portrait.":[56],"Existing":[57],"efforts":[58],"have":[59],"only":[60],"focused":[61],"on":[62,183,242],"modeling":[63],"rigid":[64],"lip":[65],"movements,":[66],"resulting":[67,166,197],"in":[68,140,167,198],"low-fidelity":[69],"videos":[70],"with":[71],"jerky":[72],"deformations.":[75],"To":[76],"address":[77],"these":[78],"challenges,":[79],"we":[80,96,121,175],"propose":[81],"novel":[83,178],"Fine-gRained":[84],"mOtioN":[85],"moDel":[86],"(FROND),":[87],"consisting":[88],"three":[90],"components.":[91],"In":[92,117,171,203],"first":[94],"component,":[95,120,174],"adopt":[97],"two-stream":[99],"encoder":[100],"capture":[102],"local":[103,136,153],"movement":[105],"keypoints":[106,213],"embed":[108],"their":[109],"overall":[110],"motion":[111,124,139,164,209,218],"context":[112],"global":[115,155],"code.":[116],"second":[119],"design":[122],"estimation":[125],"module":[126],"predict":[128],"audio-driven":[129],"movements.":[130,150,170],"This":[131,188],"enables":[132],"learning":[134],"key":[137],"point":[138],"continuous":[142,162,216],"trajectory":[143],"space":[144],"achieve":[146],"temporal":[148],"Additionally,":[151],"motions":[156],"are":[157],"fused":[158],"estimate":[160],"dense":[163,217],"field,":[165,219],"spatially":[168],"third":[173],"devise":[176],"implicit":[179,185],"image":[180],"decoder":[181,189,225],"based":[182],"neural":[186],"network.":[187],"recovers":[190],"high-frequency":[191],"information":[192],"from":[193],"input":[195],"image,":[196],"high-fidelity":[200],"face.":[202],"summary,":[204],"FROND":[206,252],"refines":[207],"trajectories":[210],"into":[214],"which":[220],"followed":[222],"by":[223],"that":[226,249],"fully":[227],"exploits":[228],"inherent":[230],"smoothness":[231],"motion.":[234],"We":[235],"conduct":[236],"quantitative":[237],"qualitative":[239],"model":[240],"evaluations":[241],"benchmark":[243],"datasets.":[244],"The":[245],"experimental":[246],"results":[247],"show":[248],"our":[250],"proposed":[251],"significantly":[253],"outperforms":[254],"state-of-the-art":[256],"baselines.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}