{"id":"https://openalex.org/W4413822497","doi":"https://doi.org/10.26599/cvm.2025.9450491","title":"MagicTalk: Implicit and Explicit Correlation Learning for Diffusion-Based Emotional Talking Face Generation","display_name":"MagicTalk: Implicit and Explicit Correlation Learning for Diffusion-Based Emotional Talking Face Generation","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4413822497","doi":"https://doi.org/10.26599/cvm.2025.9450491"},"language":"en","primary_location":{"id":"doi:10.26599/cvm.2025.9450491","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450491","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.26599/cvm.2025.9450491","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046566373","display_name":"Chenxu Zhang","orcid":"https://orcid.org/0000-0003-1645-9695"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenxu Zhang","raw_affiliation_strings":["ByteDance Inc.,San Jose,CA,USA,95110","ByteDance Inc., San Jose, CA 95110, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,San Jose,CA,USA,95110","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"ByteDance Inc., San Jose, CA 95110, USA","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407135","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-3742-7801"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["ByteDance Inc.,San Jose,CA,USA,95110","ByteDance Inc., San Jose, CA 95110, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,San Jose,CA,USA,95110","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"ByteDance Inc., San Jose, CA 95110, USA","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374710","display_name":"Jianfeng Zhang","orcid":"https://orcid.org/0000-0002-3270-0533"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Zhang","raw_affiliation_strings":["ByteDance Inc.,San Jose,CA,USA,95110","ByteDance Inc., San Jose, CA 95110, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,San Jose,CA,USA,95110","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"ByteDance Inc., San Jose, CA 95110, USA","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691898","display_name":"Hongyi Xu","orcid":"https://orcid.org/0009-0006-4455-5632"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyi Xu","raw_affiliation_strings":["ByteDance Inc.,San Jose,CA,USA,95110","ByteDance Inc., San Jose, CA 95110, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,San Jose,CA,USA,95110","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"ByteDance Inc., San Jose, CA 95110, USA","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012261844","display_name":"Guoxian Song","orcid":"https://orcid.org/0000-0002-3664-572X"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoxian Song","raw_affiliation_strings":["ByteDance Inc.,San Jose,CA,USA,95110","ByteDance Inc., San Jose, CA 95110, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,San Jose,CA,USA,95110","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"ByteDance Inc., San Jose, CA 95110, USA","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086711430","display_name":"You Xie","orcid":"https://orcid.org/0000-0001-7229-3218"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You Xie","raw_affiliation_strings":["ByteDance Inc.,San Jose,CA,USA,95110","ByteDance Inc., San Jose, CA 95110, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,San Jose,CA,USA,95110","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"ByteDance Inc., San Jose, CA 95110, USA","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081407963","display_name":"Linjie Luo","orcid":"https://orcid.org/0000-0001-6322-1175"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linjie Luo","raw_affiliation_strings":["ByteDance Inc.,San Jose,CA,USA,95110","ByteDance Inc., San Jose, CA 95110, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,San Jose,CA,USA,95110","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"ByteDance Inc., San Jose, CA 95110, USA","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071520794","display_name":"Yapeng Tian","orcid":"https://orcid.org/0000-0003-4271-5293"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yapeng Tian","raw_affiliation_strings":["University of Texas at Dallas,Richardson,TX,USA,75080","University of Texas at Dallas, Richardson, TX 75080, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX 75080, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668696","display_name":"Jiashi Feng","orcid":"https://orcid.org/0000-0001-6843-0064"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiashi Feng","raw_affiliation_strings":["ByteDance Inc.,San Jose,CA,USA,95110","ByteDance Inc., San Jose, CA 95110, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc.,San Jose,CA,USA,95110","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"ByteDance Inc., San Jose, CA 95110, USA","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101604531","display_name":"Xiaohu Guo","orcid":"https://orcid.org/0000-0002-2141-7222"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohu Guo","raw_affiliation_strings":["University of Texas at Dallas,Richardson,TX,USA,75080","University of Texas at Dallas, Richardson, TX 75080, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX 75080, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5046566373"],"corresponding_institution_ids":["https://openalex.org/I173632517"],"apc_list":null,"apc_paid":null,"fwci":2.5993,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91350498,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"11","issue":"4","first_page":"763","last_page":"779"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9936000108718872,"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":0.9936000108718872,"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":0.9879000186920166,"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":0.9222000241279602,"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/correlation","display_name":"Correlation","score":0.5854182839393616},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5812065005302429},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5483241677284241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49648338556289673},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3883131146430969},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3820975422859192},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2249152958393097},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.1411150097846985},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.12164896726608276},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09190592169761658}],"concepts":[{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5854182839393616},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5812065005302429},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5483241677284241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49648338556289673},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3883131146430969},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3820975422859192},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2249152958393097},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.1411150097846985},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.12164896726608276},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09190592169761658},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26599/cvm.2025.9450491","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450491","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d9f9c3ad4f5e4448b3a32e6e62ee4197","is_oa":true,"landing_page_url":"https://doaj.org/article/d9f9c3ad4f5e4448b3a32e6e62ee4197","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Visual Media, Vol 11, Iss 4, Pp 763-779 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.26599/cvm.2025.9450491","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450491","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2604379605","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2754447548","https://openalex.org/W2769666294","https://openalex.org/W2808631503","https://openalex.org/W2944294033","https://openalex.org/W2963290645","https://openalex.org/W2970710980","https://openalex.org/W3019952993","https://openalex.org/W3081192838","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3107666850","https://openalex.org/W3159279967","https://openalex.org/W3174763799","https://openalex.org/W3175779516","https://openalex.org/W3176721746","https://openalex.org/W3180770160","https://openalex.org/W3186090335","https://openalex.org/W3186700381","https://openalex.org/W3193508667","https://openalex.org/W3195529437","https://openalex.org/W3197199219","https://openalex.org/W3202128205","https://openalex.org/W3211147706","https://openalex.org/W4221142137","https://openalex.org/W4281730245","https://openalex.org/W4281779270","https://openalex.org/W4311137635","https://openalex.org/W4312444931","https://openalex.org/W4312959196","https://openalex.org/W4312990833","https://openalex.org/W4382469130","https://openalex.org/W4386065807","https://openalex.org/W4386066256","https://openalex.org/W4386066404","https://openalex.org/W4386071653","https://openalex.org/W4386072006","https://openalex.org/W4386072021","https://openalex.org/W4386075487","https://openalex.org/W4386076090","https://openalex.org/W4386076103","https://openalex.org/W4389212256","https://openalex.org/W4390872334","https://openalex.org/W4390872428","https://openalex.org/W4390872742","https://openalex.org/W4390872769","https://openalex.org/W4394597549","https://openalex.org/W4399344807","https://openalex.org/W4403163170","https://openalex.org/W4404199654","https://openalex.org/W4411049949","https://openalex.org/W4413822446"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2931662336","https://openalex.org/W4220667126","https://openalex.org/W2077865380","https://openalex.org/W3006817050","https://openalex.org/W4401768695","https://openalex.org/W2765597752","https://openalex.org/W2134894512","https://openalex.org/W2083375246"],"abstract_inverted_index":{"Generating":[0],"emotional":[1,18,46,66,75,91,105],"talking":[2,19,67],"faces":[3,68],"from":[4,140],"a":[5,10,70,116,130,141],"single":[6],"portrait":[7],"image":[8],"remains":[9],"significant":[11],"challenge.":[12],"The":[13],"simultaneous":[14],"achievement":[15],"of":[16,45,119,159],"expressive":[17],"and":[20,48,60,65,80,90,137,151,162],"accurate":[21],"lip-sync":[22,32],"is":[23,28],"particularly":[24],"difficult,":[25],"as":[26],"expressiveness":[27],"often":[29],"compromised":[30],"for":[31,99],"accuracy.":[33],"Prevailing":[34],"generative":[35],"works":[36],"usually":[37,77],"struggle":[38],"to":[39,41,114,121,134,145],"juggle":[40],"generate":[42],"subtle":[43,79],"variations":[44],"expression":[47],"lip-synchronized":[49],"talking.":[50],"To":[51],"address":[52],"these":[53],"challenges,":[54],"we":[55,86,128],"suggest":[56],"modeling":[57],"the":[58,95],"implicit":[59,81],"explicit":[61,111],"correlations":[62],"between":[63],"audio":[64,89,120],"with":[69,83],"unified":[71],"framework.":[72],"As":[73],"human":[74],"expressions":[76,136],"present":[78],"relations":[82],"speech":[84],"audio,":[85],"propose":[87,109],"incorporating":[88],"style":[92],"embeddings":[93],"into":[94],"diffusion-based":[96],"generation":[97,101],"process,":[98],"realistic":[100],"while":[102],"concentrating":[103],"on":[104],"expressions.":[106],"We":[107],"then":[108],"lip-based":[110],"correlation":[112],"learning":[113],"construct":[115],"strong":[117],"mapping":[118],"lip":[122,138],"motions,":[123],"assuring":[124],"lip-audio":[125],"synchronization.":[126],"Furthermore,":[127],"deploy":[129],"video-to-video":[131],"rendering":[132],"module":[133],"transfer":[135],"motions":[139],"proxy":[142],"3D":[143],"avatar":[144],"an":[146],"arbitrary":[147],"portrait.":[148],"Both":[149],"quantitatively":[150],"qualitatively,":[152],"MagicTalk":[153],"outperforms":[154],"state-of-the-art":[155],"methods":[156],"in":[157],"terms":[158],"expressiveness,":[160],"lip-sync,":[161],"perceptual":[163],"quality.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}
