{"id":"https://openalex.org/W4386363058","doi":"https://doi.org/10.1109/tcsvt.2023.3311039","title":"Stochastic Latent Talking Face Generation Toward Emotional Expressions and Head Poses","display_name":"Stochastic Latent Talking Face Generation Toward Emotional Expressions and Head Poses","publication_year":2023,"publication_date":"2023-09-01","ids":{"openalex":"https://openalex.org/W4386363058","doi":"https://doi.org/10.1109/tcsvt.2023.3311039"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3311039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3311039","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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/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":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-9245-3124","affiliations":[{"raw_affiliation_string":"School 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/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":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[{"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":"Min Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3895-5510","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7778-8807","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395059","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2763,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82331723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"34","issue":"4","first_page":"2734","last_page":"2748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"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/T11448","display_name":"Face recognition and analysis","score":0.9991000294685364,"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":0.9918000102043152,"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":0.7611094117164612},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6517017483711243},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6301707029342651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5350469350814819},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5068994164466858},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4964979290962219},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.46857500076293945},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43739399313926697},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4323643743991852},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.42614316940307617},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40115687251091003},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25656867027282715},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2330189347267151},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14330074191093445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7611094117164612},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6517017483711243},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6301707029342651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5350469350814819},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5068994164466858},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4964979290962219},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.46857500076293945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43739399313926697},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4323643743991852},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.42614316940307617},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40115687251091003},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25656867027282715},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2330189347267151},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14330074191093445},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3311039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3311039","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2082285544","https://openalex.org/W2096320828","https://openalex.org/W2133665775","https://openalex.org/W2149628368","https://openalex.org/W2168982238","https://openalex.org/W2604379605","https://openalex.org/W2890952074","https://openalex.org/W2944294033","https://openalex.org/W2950689937","https://openalex.org/W2962785568","https://openalex.org/W2962851448","https://openalex.org/W2963290645","https://openalex.org/W2964232608","https://openalex.org/W2969985801","https://openalex.org/W2973049979","https://openalex.org/W2979894294","https://openalex.org/W2981591098","https://openalex.org/W2992005611","https://openalex.org/W3006410788","https://openalex.org/W3015023262","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3093274101","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3109114891","https://openalex.org/W3109585842","https://openalex.org/W3174763799","https://openalex.org/W3180770160","https://openalex.org/W3180794345","https://openalex.org/W3186090335","https://openalex.org/W3186700381","https://openalex.org/W3187364420","https://openalex.org/W3217536461","https://openalex.org/W4200631136","https://openalex.org/W4281730245","https://openalex.org/W4281779270","https://openalex.org/W4297095647","https://openalex.org/W4309591648","https://openalex.org/W4312444931","https://openalex.org/W4367276751","https://openalex.org/W4382469130","https://openalex.org/W4386065999","https://openalex.org/W4386066256","https://openalex.org/W4386066404","https://openalex.org/W4386072021","https://openalex.org/W6617744952","https://openalex.org/W6640963894","https://openalex.org/W6711952718","https://openalex.org/W6714644935","https://openalex.org/W6745420753","https://openalex.org/W6748392304","https://openalex.org/W6752307458","https://openalex.org/W6755056417","https://openalex.org/W6767145620","https://openalex.org/W6767264202","https://openalex.org/W6771703261","https://openalex.org/W6773968666","https://openalex.org/W6795140394","https://openalex.org/W6797315367","https://openalex.org/W6849049266"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2368824897","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W2030109976","https://openalex.org/W2369260257","https://openalex.org/W2389120450","https://openalex.org/W55249799"],"abstract_inverted_index":{"Current":[0],"talking":[1,15,119,180],"face":[2,16,106,120,181],"generation":[3],"methods":[4,209],"have":[5,28],"achieved":[6],"promising":[7],"lip-synchronization":[8],"results,":[9],"while":[10],"still":[11],"struggling":[12],"to":[13,65,87,145,194],"generate":[14],"video":[17],"that":[18,30,37,47,205],"exhibits":[19],"emotional":[20,51,71],"expressions":[21,52,72,91],"and":[22,53,73,76,92,127,176,210],"head":[23,54,74,93],"poses.":[24,94],"Studies":[25],"in":[26],"psychology":[27],"demonstrated":[29],"people":[31],"may":[32],"manifest":[33],"diverse":[34,126],"facial":[35,63,129,198],"animations":[36],"follow":[38],"a":[39,102,112,139,164,170,177,186],"time-varying":[40,60],"distribution.":[41,135,201],"This":[42,151],"presents":[43],"two":[44],"stochastic":[45,68,128],"challenges":[46],"make":[48],"generating":[49],"appropriate":[50],"poses":[55],"difficult:":[56],"(1)":[57],"modelling":[58],"the":[59,67,79,97,132,147,154,196],"distribution":[61,82],"of":[62,70,159],"deformations":[64],"synthesize":[66],"dynamics":[69,130],"poses,":[75],"(2)":[77],"estimating":[78],"complex":[80,197],"motion":[81,134,168,174,199],"with":[83],"given":[84],"audio":[85],"features":[86],"capture":[88],"ambiguous":[89],"audio-related":[90],"To":[95],"address":[96],"above":[98],"issues,":[99],"we":[100,137,184],"present":[101],"Stochastic":[103],"Latent":[104],"talkIng":[105],"Generation":[107],"mOdel":[108],"(SLIGO),":[109],"which":[110],"builds":[111],"deep":[113,148],"state":[114],"space":[115],"model":[116,124,195],"(SSM)":[117],"for":[118,166,172,179],"generation.":[121],"The":[122],"SLIGO":[123,206],"captures":[125],"via":[131],"latent":[133,167],"Additionally,":[136],"devise":[138],"dynamic":[140],"variational":[141],"autoencoder":[142],"(DVAE)":[143],"method":[144,152],"optimize":[146],"SSM":[149,160],"model.":[150],"decomposes":[153],"Evidence":[155],"Lower":[156],"BOund":[157],"(ELBO)":[158],"into":[161],"three":[162],"components:":[163],"posterior":[165],"encoding,":[169],"prior":[171,200],"audio-driven":[173],"prediction,":[175],"likelihood":[178],"decoding.":[182],"Furthermore,":[183],"propose":[185],"novel":[187],"mixer":[188],"continuous":[189],"normalizing":[190],"flow":[191],"(CNF)":[192],"module":[193],"Experimental":[202],"results":[203],"demonstrate":[204],"outperforms":[207],"existing":[208],"achieves":[211],"state-of-the-art":[212],"performance.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
