{"id":"https://openalex.org/W7127905232","doi":"https://doi.org/10.1007/s11263-025-02695-x","title":"Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait","display_name":"Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7127905232","doi":"https://doi.org/10.1007/s11263-025-02695-x"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02695-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-025-02695-x","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","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/A5125145817","display_name":"Chaolong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]},{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Chaolong Yang","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, L69 7ZX, UK","Department of Mechatronics and Robotics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, L69 7ZX, UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Mechatronics and Robotics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047420717","display_name":"Kai Yao","orcid":"https://orcid.org/0000-0003-4623-0365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Yao","raw_affiliation_strings":["Ant Group, Hangzhou, 310000, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, 310000, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119910911","display_name":"Xi Yang","orcid":"https://orcid.org/0009-0007-4874-7831"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyao Yan","raw_affiliation_strings":["School of Robotic, Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, China"],"affiliations":[{"raw_affiliation_string":"School of Robotic, Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011959564","display_name":"Chenru Jiang","orcid":"https://orcid.org/0000-0001-8845-3511"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenru Jiang","raw_affiliation_strings":["Digital Innovation Research Center, Duke Kunshan University, Kunshan, 215316, China"],"affiliations":[{"raw_affiliation_string":"Digital Innovation Research Center, Duke Kunshan University, Kunshan, 215316, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125244336","display_name":"Weiguang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]},{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Weiguang Zhao","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, L69 7ZX, UK","Department of Foundational Mathematics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, L69 7ZX, UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Foundational Mathematics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101427624","display_name":"Jie Sun","orcid":"https://orcid.org/0000-0002-5196-7268"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Sun","raw_affiliation_strings":["Department of Mechatronics and Robotics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, China"],"affiliations":[{"raw_affiliation_string":"Department of Mechatronics and Robotics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125243206","display_name":"Guangliang Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guangliang Cheng","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, L69 7ZX, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, L69 7ZX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125160125","display_name":"Yifei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I24193003","display_name":"Ricoh (Japan)","ror":"https://ror.org/02h4myp42","country_code":"JP","type":"company","lineage":["https://openalex.org/I24193003"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yifei Zhang","raw_affiliation_strings":["Ricoh Software Research Center, Beijing, 100027, China"],"affiliations":[{"raw_affiliation_string":"Ricoh Software Research Center, Beijing, 100027, China","institution_ids":["https://openalex.org/I24193003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125240971","display_name":"Bin Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Dong","raw_affiliation_strings":["Digital Innovation Research Center, Duke Kunshan University, Kunshan, 215316, China"],"affiliations":[{"raw_affiliation_string":"Digital Innovation Research Center, Duke Kunshan University, Kunshan, 215316, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103236934","display_name":"Kaizhu Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaizhu Huang","raw_affiliation_strings":["Digital Innovation Research Center, Duke Kunshan University, Kunshan, 215316, China"],"affiliations":[{"raw_affiliation_string":"Digital Innovation Research Center, Duke Kunshan University, Kunshan, 215316, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5101427624"],"corresponding_institution_ids":["https://openalex.org/I69356397"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28216319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.7587000131607056,"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":0.7587000131607056,"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":0.1678999960422516,"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":0.04450000077486038,"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":0.5884000062942505},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5253000259399414},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5131999850273132},{"id":"https://openalex.org/keywords/face-hallucination","display_name":"Face hallucination","score":0.5113999843597412},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4796999990940094},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4327000081539154},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3580999970436096},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.31790000200271606},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3158999979496002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6276000142097473},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5131999850273132},{"id":"https://openalex.org/C54654163","wikidata":"https://www.wikidata.org/wiki/Q5428359","display_name":"Face hallucination","level":5,"score":0.5113999843597412},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4327000081539154},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.31790000200271606},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3091999888420105},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2779989122","wikidata":"https://www.wikidata.org/wiki/Q15889487","display_name":"Perspective distortion","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02695-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-025-02695-x","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4174618055","display_name":null,"funder_award_id":"No. 92370119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5237436191","display_name":null,"funder_award_id":"No. 62376113","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":33,"referenced_works":["https://openalex.org/W2237250383","https://openalex.org/W2738406145","https://openalex.org/W2760103357","https://openalex.org/W2884460600","https://openalex.org/W2944294033","https://openalex.org/W2963644257","https://openalex.org/W2969985801","https://openalex.org/W2981767644","https://openalex.org/W3081492798","https://openalex.org/W3096831136","https://openalex.org/W3180770160","https://openalex.org/W3197199219","https://openalex.org/W3204680331","https://openalex.org/W4200631136","https://openalex.org/W4214626920","https://openalex.org/W4221145616","https://openalex.org/W4310379947","https://openalex.org/W4312301053","https://openalex.org/W4312473638","https://openalex.org/W4312671789","https://openalex.org/W4312933868","https://openalex.org/W4312967111","https://openalex.org/W4385801140","https://openalex.org/W4386072021","https://openalex.org/W4386075487","https://openalex.org/W4386075576","https://openalex.org/W4388979610","https://openalex.org/W4390872428","https://openalex.org/W4403791206","https://openalex.org/W4404199654","https://openalex.org/W4405436952","https://openalex.org/W4409365674","https://openalex.org/W4409369524"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-02-07T00:00:00"}
