{"id":"https://openalex.org/W4399665715","doi":"https://doi.org/10.1109/tcsvt.2024.3414412","title":"Audio-Semantic Enhanced Pose-Driven Talking Head Generation","display_name":"Audio-Semantic Enhanced Pose-Driven Talking Head Generation","publication_year":2024,"publication_date":"2024-06-14","ids":{"openalex":"https://openalex.org/W4399665715","doi":"https://doi.org/10.1109/tcsvt.2024.3414412"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3414412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3414412","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/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":true,"raw_author_name":"Meng Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Shandong Jianzhu University, Jinan, China","Department of Computer Science and Technology, Shandong Jianzhu University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Shandong Jianzhu University, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103366660","display_name":"Da Li","orcid":"https://orcid.org/0009-0001-1300-4129"},"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":"Da Li","raw_affiliation_strings":["Department of Computer Science and Technology, Shandong Jianzhu University, Jinan, China","Department of Computer Science and Technology, Shandong Jianzhu University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Shandong Jianzhu University, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101547882","display_name":"Yongqiang Li","orcid":"https://orcid.org/0000-0002-7586-9232"},"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":"Yongqiang Li","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"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/A5072768866","display_name":"Xuemeng Song","orcid":"https://orcid.org/0000-0002-5274-4197"},"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":"Xuemeng Song","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China","School of Computer Science and Technology, Shandong University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]},{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"last","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"]},{"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"]}],"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","School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), China"],"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"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100457438"],"corresponding_institution_ids":["https://openalex.org/I44445938"],"apc_list":null,"apc_paid":null,"fwci":2.7538,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90326714,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"34","issue":"11","first_page":"11056","last_page":"11069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9580000042915344,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9496999979019165,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.7498806118965149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4629339575767517},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4547008275985718},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4349597692489624},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4179183840751648},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36145323514938354},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3479241132736206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498806118965149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4629339575767517},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4547008275985718},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4349597692489624},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4179183840751648},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36145323514938354},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3479241132736206},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/tcsvt.2024.3414412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3414412","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/G3881774828","display_name":null,"funder_award_id":"ZR2022YQ59","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"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/G5422811002","display_name":null,"funder_award_id":"U23A20315","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6292720726","display_name":null,"funder_award_id":"62376137","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"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1910513476","https://openalex.org/W2048458228","https://openalex.org/W2110940238","https://openalex.org/W2594690981","https://openalex.org/W2603777577","https://openalex.org/W2604379605","https://openalex.org/W2738406145","https://openalex.org/W2790649793","https://openalex.org/W2884460600","https://openalex.org/W2914217321","https://openalex.org/W2944294033","https://openalex.org/W2962770929","https://openalex.org/W2963073614","https://openalex.org/W2963081548","https://openalex.org/W2963150697","https://openalex.org/W2963290645","https://openalex.org/W2964449965","https://openalex.org/W2964559396","https://openalex.org/W2979894294","https://openalex.org/W3006410788","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3107666850","https://openalex.org/W3161033181","https://openalex.org/W3168931281","https://openalex.org/W3176721746","https://openalex.org/W3177150198","https://openalex.org/W3180391059","https://openalex.org/W3186090335","https://openalex.org/W3187364420","https://openalex.org/W3195529437","https://openalex.org/W3197199219","https://openalex.org/W3202128205","https://openalex.org/W3204680331","https://openalex.org/W3211147706","https://openalex.org/W4200150166","https://openalex.org/W4200174933","https://openalex.org/W4200631136","https://openalex.org/W4210657261","https://openalex.org/W4225760288","https://openalex.org/W4256199362","https://openalex.org/W4283818626","https://openalex.org/W4297095647","https://openalex.org/W4297793551","https://openalex.org/W4304087182","https://openalex.org/W4312301053","https://openalex.org/W4312772581","https://openalex.org/W4312933868","https://openalex.org/W4367276751","https://openalex.org/W4372262415","https://openalex.org/W4381886216","https://openalex.org/W4385289414","https://openalex.org/W4385767717","https://openalex.org/W4386072021","https://openalex.org/W4386075487","https://openalex.org/W4386363058","https://openalex.org/W4389879878","https://openalex.org/W4390872427","https://openalex.org/W4390872428","https://openalex.org/W4390874567","https://openalex.org/W4392824768","https://openalex.org/W4394597549","https://openalex.org/W4394698479","https://openalex.org/W6640090968","https://openalex.org/W6677618333","https://openalex.org/W6748181857","https://openalex.org/W6774285787","https://openalex.org/W6811548253","https://openalex.org/W6860709368"],"related_works":["https://openalex.org/W3097502728","https://openalex.org/W2113206756","https://openalex.org/W3009949491","https://openalex.org/W1927475415","https://openalex.org/W2613352840","https://openalex.org/W2379547295","https://openalex.org/W2180861836","https://openalex.org/W2079398652","https://openalex.org/W4388166999","https://openalex.org/W2724652190"],"abstract_inverted_index":{"Talking":[0],"head":[1,49,89,115,132],"generation,":[2],"aiming":[3],"to":[4,109,144],"create":[5],"photo-realistic":[6],"videos":[7],"from":[8],"a":[9,19,83,95,102,161],"single":[10],"reference":[11],"image":[12],"and":[13,48,112,126,168],"audio":[14,46],"input,":[15],"has":[16],"emerged":[17],"as":[18,52],"vibrant":[20],"area":[21],"of":[22,63,73,140,149,179],"interest":[23],"within":[24],"the":[25,42,60,138,147,150,154,177],"computer":[26],"vision":[27],"community.":[28],"Despite":[29],"notable":[30],"advancements,":[31],"several":[32],"challenges":[33],"remain":[34],"unaddressed.":[35],"For":[36],"instance,":[37],"many":[38],"existing":[39],"approaches":[40],"overlook":[41],"nuanced":[43],"relationship":[44],"between":[45],"semantics":[47,139],"movement,":[50],"such":[51],"nodding":[53],"in":[54,67],"agreement":[55],"during":[56],"affirmative":[57],"expressions.":[58],"Additionally,":[59],"visual":[61],"quality":[62],"generated":[64],"content,":[65],"particularly":[66],"depicting":[68],"teeth,":[69,155],"often":[70],"falls":[71],"short":[72],"achieving":[74],"authentic":[75,111],"realism.":[76],"To":[77],"address":[78],"these":[79],"limitations,":[80],"we":[81],"introduce":[82],"groundbreaking":[84],"audio-semantic":[85],"enhanced":[86],"pose-driven":[87],"talking":[88,114],"generation":[90],"method.":[91,181],"Our":[92],"approach":[93],"encompasses":[94],"multimodal":[96,118],"3DMM":[97,119],"parameter":[98,120],"prediction":[99,121],"network":[100,122,163],"alongside":[101],"high-fidelity":[103],"video":[104,157],"synthesis":[105,158],"network,":[106],"meticulously":[107],"designed":[108],"produce":[110],"high-quality":[113],"videos.":[116],"The":[117],"harnesses":[123],"both":[124,166],"acoustic":[125],"audio-deduced":[127],"semantic":[128],"information,":[129],"facilitating":[130],"accurate":[131],"pose":[133],"predictions":[134],"that":[135],"resonate":[136],"with":[137],"spoken":[141],"words.":[142],"Furthermore,":[143],"significantly":[145],"improve":[146],"depiction":[148],"mouth":[151],"area,":[152],"especially":[153],"our":[156,180],"stage":[159],"incorporates":[160],"mouth-enhanced":[162],"augmented":[164],"by":[165],"local":[167],"global":[169],"discriminators.":[170],"Comprehensive":[171],"evaluations":[172],"across":[173],"diverse":[174],"metrics":[175],"affirm":[176],"superiority":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}