{"id":"https://openalex.org/W7128929883","doi":"https://doi.org/10.1145/3788691","title":"PoseTalk: Exploring Text- and Audio-Based Pose Control for One-Shot Talking Face Generation","display_name":"PoseTalk: Exploring Text- and Audio-Based Pose Control for One-Shot Talking Face Generation","publication_year":2026,"publication_date":"2026-02-14","ids":{"openalex":"https://openalex.org/W7128929883","doi":"https://doi.org/10.1145/3788691"},"language":"en","primary_location":{"id":"doi:10.1145/3788691","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3788691","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5126012265","display_name":"Jun Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Ling","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China and Shanghai Key Laboratory of Collaborative Computing in Spacial Heterogeneous Networks, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7260-7141","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China and Shanghai Key Laboratory of Collaborative Computing in Spacial Heterogeneous Networks, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiwen Wang","orcid":"https://orcid.org/0009-0007-9646-0720"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Wang","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-9646-0720","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126026836","display_name":"Han Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Xue","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4699-4701","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940353","display_name":"Rong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Xie","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8261-5337","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101558452","display_name":"Liwei Song","orcid":"https://orcid.org/0000-0002-7124-5182"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Song","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China and MOE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7124-5182","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China and MOE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15096524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"3","first_page":"1","last_page":"24"},"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":0.6025000214576721,"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":0.6025000214576721,"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":0.3684000074863434,"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":0.004399999976158142,"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/face","display_name":"Face (sociological concept)","score":0.6449999809265137},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6086000204086304},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6031000018119812},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5863000154495239},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48660001158714294},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3603000044822693},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.3294000029563904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8889999985694885},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6449999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6097999811172485},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6086000204086304},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6031000018119812},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5267000198364258},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44510000944137573},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2780549717","wikidata":"https://www.wikidata.org/wiki/Q3409626","display_name":"Human head","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3788691","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3788691","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4950456183","display_name":null,"funder_award_id":"BP0719010","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G6779038178","display_name":null,"funder_award_id":"62431015 and 62571317","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/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2604379605","https://openalex.org/W2726515241","https://openalex.org/W2933138175","https://openalex.org/W2944294033","https://openalex.org/W2962785568","https://openalex.org/W3019952993","https://openalex.org/W3180794345","https://openalex.org/W3195529437","https://openalex.org/W3204680331","https://openalex.org/W3211147706","https://openalex.org/W4297981470","https://openalex.org/W4309617235","https://openalex.org/W4312933868","https://openalex.org/W4313145975","https://openalex.org/W4390872116","https://openalex.org/W4390872769","https://openalex.org/W4394597549","https://openalex.org/W4399740326","https://openalex.org/W4401483653","https://openalex.org/W4401807241","https://openalex.org/W4402760804","https://openalex.org/W4403132043"],"related_works":[],"abstract_inverted_index":{"Although":[0],"audio-driven":[1],"talking":[2],"face":[3],"generation":[4,212],"has":[5],"witnessed":[6],"significant":[7],"advances":[8],"in":[9,64,222],"recent":[10],"years,":[11],"two":[12,110,159],"problems":[13],"remain":[14,58],"to":[15,61,85,90,105,150,172,189,209],"be":[16],"solved.":[17],"First,":[18,89],"the":[19,24,32,41,62,66,92,115,129,133,137,180],"existing":[20],"models":[21],"cannot":[22],"control":[23],"long-term":[25,50,138],"head":[26,46,51,71,107,130,141,152,225],"actions":[27],"as":[28,40],"humans":[29],"expect,":[30],"because":[31],"audio":[33,95,117,123],"can":[34,201],"only":[35],"provide":[36],"short-term":[37,125],"cues,":[38],"such":[39],"rhythms":[42],"and":[43,53,73,118,154,164,179,206,214,228],"sentiments,":[44],"for":[45,69],"movements.":[47],"Second,":[48,143],"generating":[49],"poses":[52],"ensuring":[54],"accurate":[55,155],"lip":[56,156,185],"motions":[57,108,157,171,186],"challenging":[59],"due":[60],"difficulty":[63],"harnessing":[65],"optimization":[67],"process":[68],"large-scale":[70],"movements":[72,153],"small-scale":[74],"mouth":[75],"motions.":[76,142,226],"In":[77],"this":[78],"study,":[79],"we":[80,97,144],"propose":[81,98,145],"a":[82,99,146],"novel":[83],"method":[84,200],"address":[86],"these":[87],"issues.":[88],"alleviate":[91],"limitations":[93],"of":[94,112,140],"conditions,":[96],"Pose":[100],"Latent":[101],"Diffusion":[102],"(PLD)":[103],"model":[104,218],"generate":[106],"from":[109,187],"kinds":[111],"input":[113,116],"modalities:":[114],"user-controlled":[119],"text":[120,134],"prompts.":[121],"The":[122,166],"provides":[124],"rhythm":[126],"correspondence":[127],"with":[128,176],"movements,":[131],"while":[132],"prompts":[135],"describe":[136],"semantics":[139],"refinement-based":[147],"learning":[148],"strategy":[149],"synthesize":[151],"using":[158],"cascaded":[160],"networks,":[161],"namely":[162],"CoarseNet":[163,167],"RefineNet.":[165],"estimates":[168,183],"coarse":[169],"global":[170],"produce":[173],"animated":[174],"images":[175],"changed":[177],"poses,":[178],"RefineNet":[181],"progressively":[182],"finer":[184],"low":[188],"high":[190],"resolutions,":[191],"yielding":[192],"improved":[193],"lip-synchronization":[194],"performance.":[195],"Experiments":[196],"demonstrate":[197],"that":[198],"our":[199,215],"achieve":[202],"better":[203],"pose":[204,211],"diversity":[205],"realness":[207],"compared":[208],"audio-based":[210],"baselines,":[213],"video":[216],"generator":[217],"outperforms":[219],"state-of-the-art":[220],"methods":[221],"synthesizing":[223],"natural":[224],"Projects":[227],"demos":[229],"are":[230],"available":[231],"at":[232],"https://junleen.github.io/projects/posetalk":[233],".":[234]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-15T00:00:00"}
