{"id":"https://openalex.org/W4386076090","doi":"https://doi.org/10.1109/cvpr52729.2023.01330","title":"LipFormer: High-fidelity and Generalizable Talking Face Generation with A Pre-learned Facial Codebook","display_name":"LipFormer: High-fidelity and Generalizable Talking Face Generation with A Pre-learned Facial Codebook","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386076090","doi":"https://doi.org/10.1109/cvpr52729.2023.01330"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.01330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.01330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5100368334","display_name":"Jiayu Wang","orcid":"https://orcid.org/0000-0003-4497-2891"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiayu Wang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103326213","display_name":"Kang Zhao","orcid":"https://orcid.org/0009-0000-3053-3965"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kang Zhao","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449697","display_name":"Shiwei Zhang","orcid":"https://orcid.org/0000-0002-6929-5295"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiwei Zhang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039538233","display_name":"Yingya Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingya Zhang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103003762","display_name":"Yujun Shen","orcid":"https://orcid.org/0000-0003-3801-6705"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Shen","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911374","display_name":"Deli Zhao","orcid":"https://orcid.org/0000-0002-8838-578X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deli Zhao","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057864403","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-4220-2634"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingren Zhou","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100368334"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":3.6571,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94680712,"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":"13844","last_page":"13853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9986000061035156,"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":0.9925000071525574,"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":0.8263423442840576},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.7199548482894897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6385093331336975},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5619295239448547},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5218138694763184},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46064215898513794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4346862733364105},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41200006008148193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263423442840576},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.7199548482894897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6385093331336975},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5619295239448547},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5218138694763184},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46064215898513794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4346862733364105},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41200006008148193},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52729.2023.01330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.01330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2133665775","https://openalex.org/W2331128040","https://openalex.org/W2547875792","https://openalex.org/W2594690981","https://openalex.org/W2738406145","https://openalex.org/W2752796333","https://openalex.org/W2782422271","https://openalex.org/W2803705807","https://openalex.org/W2884460600","https://openalex.org/W2890952074","https://openalex.org/W2896446917","https://openalex.org/W2944294033","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2963799213","https://openalex.org/W2963926543","https://openalex.org/W2964449965","https://openalex.org/W2964559396","https://openalex.org/W2990452356","https://openalex.org/W3019952993","https://openalex.org/W3034257218","https://openalex.org/W3034688736","https://openalex.org/W3035574324","https://openalex.org/W3035600682","https://openalex.org/W3047146825","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3109114891","https://openalex.org/W3111551570","https://openalex.org/W3174763799","https://openalex.org/W3177583232","https://openalex.org/W3180355996","https://openalex.org/W3180770160","https://openalex.org/W3186090335","https://openalex.org/W3187364420","https://openalex.org/W3197199219","https://openalex.org/W3211147706","https://openalex.org/W4200150166","https://openalex.org/W4283373024","https://openalex.org/W4283818626","https://openalex.org/W4287864845","https://openalex.org/W4312301053","https://openalex.org/W4312326192","https://openalex.org/W4312955540","https://openalex.org/W4312959196","https://openalex.org/W4312990833","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6702130928","https://openalex.org/W6729448088","https://openalex.org/W6739901393","https://openalex.org/W6748181857","https://openalex.org/W6750008037","https://openalex.org/W6751178058","https://openalex.org/W6753084572","https://openalex.org/W6753894364","https://openalex.org/W6754392867","https://openalex.org/W6757199795","https://openalex.org/W6771661716","https://openalex.org/W6774418182","https://openalex.org/W6780226713","https://openalex.org/W6780875980","https://openalex.org/W6781360310","https://openalex.org/W6783376789","https://openalex.org/W6785212809","https://openalex.org/W6794018690","https://openalex.org/W6810321838","https://openalex.org/W6811134278","https://openalex.org/W6839082156","https://openalex.org/W6840608358"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W2377486419","https://openalex.org/W2943202426","https://openalex.org/W2163679795","https://openalex.org/W2736714427","https://openalex.org/W2137816434","https://openalex.org/W2017956276","https://openalex.org/W2048606991"],"abstract_inverted_index":{"Generating":[0],"a":[1,11,30,39,49,98],"talking":[2,57,75,176],"face":[3,44,70,76,121,129,177],"video":[4],"from":[5],"the":[6,62,66,74,85,103,108,127,131,135,140],"input":[7,113],"audio":[8,114],"sequence":[9,110],"is":[10,162],"practical":[12],"yet":[13],"challenging":[14],"task.":[15],"Most":[16],"existing":[17],"methods":[18,182],"either":[19],"fail":[20],"to":[21,28,61,83,101,130,138,164,180,186],"capture":[22],"fine":[23],"facial":[24],"details":[25],"or":[26],"need":[27],"train":[29],"specific":[31],"model":[32,102],"for":[33],"each":[34],"identity.":[35],"We":[36,116],"argue":[37],"that":[38,52,170],"codebook":[40,67],"pre-learned":[41],"on":[42,112],"high-quality":[43],"images":[45,160],"can":[46,152,172],"serve":[47],"as":[48,79],"useful":[50],"prior":[51],"facilitates":[53],"high-fidelity":[54],"and":[55,106,161,183],"generalizable":[56],"head":[58],"synthesis.":[59],"Thanks":[60],"strong":[63],"capability":[64],"of":[65,87,142,156],"in":[68,134,159],"representing":[69],"textures,":[71],"we":[72,95],"simplify":[73],"generation":[77],"task":[78],"finding":[80],"proper":[81],"lip-codes":[82,109],"characterize":[84],"variation":[86],"lips":[88],"during":[89],"portrait":[90],"talking.":[91],"To":[92],"this":[93,149],"end,":[94],"propose":[96],"LipFormer,":[97],"Transformer-based":[99],"framework":[100],"audio-visual":[104],"coherence":[105],"predict":[107],"based":[111],"features.":[115],"further":[117],"introduce":[118],"an":[119],"adaptive":[120],"warping":[122],"module,":[123],"which":[124],"helps":[125],"warp":[126],"reference":[128],"target":[132],"pose":[133],"feature":[136],"space,":[137],"alleviate":[139],"difficulty":[141],"lip-code":[143],"prediction":[144],"under":[145],"different":[146],"poses.":[147],"By":[148],"means,":[150],"LipFormer":[151,171],"make":[153],"better":[154],"use":[155],"prelearned":[157],"priors":[158],"robust":[163],"posture":[165],"change.":[166],"Extensive":[167],"experiments":[168],"show":[169],"produce":[173],"more":[174],"realistic":[175],"videos":[178],"compared":[179],"previous":[181],"faithfully":[184],"generalize":[185],"unseen":[187],"identities.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}
