{"id":"https://openalex.org/W4372268734","doi":"https://doi.org/10.1109/icassp49357.2023.10096593","title":"Memory-Augmented Contrastive Learning for Talking Head Generation","display_name":"Memory-Augmented Contrastive Learning for Talking Head Generation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372268734","doi":"https://doi.org/10.1109/icassp49357.2023.10096593"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102003658","display_name":"Jianrong Wang","orcid":"https://orcid.org/0000-0002-8980-1634"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianrong Wang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102315536","display_name":"Yaxin Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxin Zhao","raw_affiliation_strings":["Tianjin University,Tianjin International Engineering Institute,Tianjin,China","Tianjin International Engineering Institute, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin International Engineering Institute,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin International Engineering Institute, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051780992","display_name":"Hongkai Fan","orcid":"https://orcid.org/0009-0003-7354-9360"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongkai Fan","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051440813","display_name":"Tianyi Xu","orcid":"https://orcid.org/0000-0001-6697-2492"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Xu","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108616991","display_name":"Qi Li","orcid":"https://orcid.org/0000-0002-7905-2860"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Li","raw_affiliation_strings":["Tianjin University,School of Electrical and Information Engineering,Tianjin,China","School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,School of Electrical and Information Engineering,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444241","display_name":"Sen Li","orcid":"https://orcid.org/0000-0002-2818-2286"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Li","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418783","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-2011-2873"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China","The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China","institution_ids":[]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9979000091552734,"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":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.8302739858627319},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.7774078249931335},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5852367877960205},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.584314227104187},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5239462852478027},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5220463275909424},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5216510891914368},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5141644477844238},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5066929459571838},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.480436772108078},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4349070191383362},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3890960216522217},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3229902386665344},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.21165302395820618},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.15032944083213806}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302739858627319},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.7774078249931335},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5852367877960205},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.584314227104187},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5239462852478027},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5220463275909424},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5216510891914368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5141644477844238},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5066929459571838},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.480436772108078},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4349070191383362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3890960216522217},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3229902386665344},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.21165302395820618},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.15032944083213806},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.41999998688697815}],"awards":[],"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":20,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2162220380","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2888888638","https://openalex.org/W2944294033","https://openalex.org/W2963081548","https://openalex.org/W2964559396","https://openalex.org/W2971634123","https://openalex.org/W2979894294","https://openalex.org/W3008402854","https://openalex.org/W3015734344","https://openalex.org/W3019952993","https://openalex.org/W3034464039","https://openalex.org/W3107666850","https://openalex.org/W3109114891","https://openalex.org/W3115964123","https://openalex.org/W3163112956","https://openalex.org/W3203953535","https://openalex.org/W4245793875"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2532377291","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2617644139","https://openalex.org/W2535923857","https://openalex.org/W4400097232","https://openalex.org/W1976926596","https://openalex.org/W4310844315","https://openalex.org/W3020604125"],"abstract_inverted_index":{"Given":[0],"one":[1],"reference":[2],"facial":[3,103,116],"image":[4],"and":[5,43,107],"a":[6,18,25,62],"piece":[7],"of":[8,114,123],"speech":[9,36,82],"as":[10],"input,":[11],"talking":[12,20],"head":[13,21,30,44],"generation":[14],"aims":[15],"to":[16,78,99,121],"synthesize":[17],"realistic-looking":[19],"video.":[22],"However,":[23],"generating":[24],"lip-synchronized":[26],"video":[27],"with":[28],"natural":[29],"movements":[31],"is":[32,49,118],"challenging.":[33],"The":[34,127],"same":[35],"clip":[37],"can":[38],"generate":[39,100],"multiple":[40,80,101],"possible":[41],"lip":[42],"movements,":[45],"that":[46,111,122],"is,":[47],"there":[48],"no":[50],"one-to-one":[51],"mapping":[52,83],"relationship":[53],"between":[54],"them.":[55],"To":[56],"overcome":[57],"this":[58],"problem,":[59],"we":[60,87],"propose":[61],"Speech":[63],"Feature":[64],"Extractor":[65],"(SFE)":[66],"based":[67],"on":[68],"memory-augmented":[69],"self-supervised":[70],"contrastive":[71],"learning,":[72],"which":[73],"introduces":[74],"the":[75,89,95,112,124],"memory":[76],"module":[77],"store":[79],"different":[81],"results.":[84],"In":[85],"addition,":[86],"introduce":[88],"Mixed":[90],"Density":[91],"Networks":[92],"(MDN)":[93],"into":[94],"landmark":[96],"regression":[97],"task":[98],"predicted":[102],"landmarks.":[104],"Extensive":[105],"qualitative":[106],"quantitative":[108],"experiments":[109],"show":[110],"quality":[113],"our":[115],"animation":[117],"significantly":[119],"superior":[120],"state-of-the-art":[125],"(SOTA).":[126],"code":[128],"has":[129],"been":[130],"released":[131],"at":[132],"https://github.com/Yaxinzhao97/MACL.git.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
