{"id":"https://openalex.org/W4412984985","doi":"https://doi.org/10.1109/tcsvt.2025.3595900","title":"StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion","display_name":"StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion","publication_year":2025,"publication_date":"2025-08-05","ids":{"openalex":"https://openalex.org/W4412984985","doi":"https://doi.org/10.1109/tcsvt.2025.3595900"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3595900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3595900","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":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/10836","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101726756","display_name":"Haoxin Yang","orcid":"https://orcid.org/0009-0008-5988-9816"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoxin Yang","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103551366","display_name":"Weihong Chen","orcid":"https://orcid.org/0009-0005-5332-7802"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihong Chen","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027872024","display_name":"Xuemiao Xu","orcid":"https://orcid.org/0000-0002-8006-3663"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemiao Xu","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101588348","display_name":"Cheng Xu","orcid":"https://orcid.org/0000-0002-4281-6214"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Cheng Xu","raw_affiliation_strings":["Centre for Smart Health, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","Centre for Smart Health, The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Centre for Smart Health, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Centre for Smart Health, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056219778","display_name":"Peng Xiao","orcid":"https://orcid.org/0000-0002-9494-8948"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Xiao","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101442652","display_name":"Chenghua Sun","orcid":"https://orcid.org/0000-0002-6325-8178"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cuifeng Sun","raw_affiliation_strings":["Cloud Computing Center, Chinese Academy of Sciences, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"Cloud Computing Center, Chinese Academy of Sciences, Dongguan, China","institution_ids":["https://openalex.org/I4210144487","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047172505","display_name":"Shaoyu Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150595","display_name":"Guangzhou Electronic Technology (China)","ror":"https://ror.org/03rq35s79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150595"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoyu Huang","raw_affiliation_strings":["Guangzhou Yichuang Information Technology Company Ltd., Guangzhou, China","Guangzhou Yichuang Information Technology Co., Ltd., Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangzhou Yichuang Information Technology Company Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I4210150595"]},{"raw_affiliation_string":"Guangzhou Yichuang Information Technology Co., Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I4210150595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056103024","display_name":"Shengfeng He","orcid":"https://orcid.org/0000-0002-3802-4644"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shengfeng He","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Bras Basah, Singapore","School of Computing and Information Systems, Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Bras Basah, Singapore","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101726756"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17566881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"1","first_page":"817","last_page":"831"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9871000051498413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7604041695594788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6558586359024048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5846104621887207},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5690370798110962},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.500208854675293},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49846863746643066},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46348837018013},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2414710521697998},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19121557474136353},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0666559636592865}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7604041695594788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6558586359024048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5846104621887207},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5690370798110962},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.500208854675293},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49846863746643066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46348837018013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2414710521697998},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19121557474136353},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0666559636592865},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2025.3595900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3595900","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"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-11838","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10836","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TCSVT.2025.3595900","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-11838","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10836","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TCSVT.2025.3595900","raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5474022296","display_name":null,"funder_award_id":"2023YFE0202700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2101032778","https://openalex.org/W2769237672","https://openalex.org/W2797184202","https://openalex.org/W2962896489","https://openalex.org/W2964221239","https://openalex.org/W3094502228","https://openalex.org/W3126541466","https://openalex.org/W3136525061","https://openalex.org/W3183950642","https://openalex.org/W3202431232","https://openalex.org/W3205327953","https://openalex.org/W3211937532","https://openalex.org/W4225557002","https://openalex.org/W4226016257","https://openalex.org/W4304083983","https://openalex.org/W4312249545","https://openalex.org/W4312417903","https://openalex.org/W4312797994","https://openalex.org/W4313068951","https://openalex.org/W4319300086","https://openalex.org/W4321488257","https://openalex.org/W4323269352","https://openalex.org/W4323795150","https://openalex.org/W4379034064","https://openalex.org/W4381946531","https://openalex.org/W4385245566","https://openalex.org/W4385767582","https://openalex.org/W4386075813","https://openalex.org/W4386076485","https://openalex.org/W4386113242","https://openalex.org/W4387963301","https://openalex.org/W4388663090","https://openalex.org/W4389665533","https://openalex.org/W4390190181","https://openalex.org/W4390871931","https://openalex.org/W4390873166","https://openalex.org/W4390873435","https://openalex.org/W4390873784","https://openalex.org/W4390874241","https://openalex.org/W4390874423","https://openalex.org/W4390874574","https://openalex.org/W4392151693","https://openalex.org/W4392543688","https://openalex.org/W4394597906","https://openalex.org/W4399358236","https://openalex.org/W4399727767","https://openalex.org/W4401506925","https://openalex.org/W4401808672","https://openalex.org/W4402703028","https://openalex.org/W4402715909","https://openalex.org/W4402727415","https://openalex.org/W4402952304","https://openalex.org/W4405079025","https://openalex.org/W4405800723","https://openalex.org/W4414197453","https://openalex.org/W4415707905"],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W3150905897","https://openalex.org/W2123263858","https://openalex.org/W2736638679","https://openalex.org/W4313046826","https://openalex.org/W1968716783"],"abstract_inverted_index":{"Monocular":[0],"3D":[1,69,90,130,218],"human":[2,219],"pose":[3,70,91,107,118,134,150,196,220],"estimation":[4],"remains":[5],"a":[6,137,163],"challenging":[7],"task":[8],"due":[9],"to":[10,17,48,97,173],"inherent":[11],"depth":[12],"ambiguities":[13],"and":[14,39,53,64,93,103,147,188,194,214],"occlusions.":[15],"Compared":[16],"traditional":[18],"methods":[19,45],"based":[20],"on":[21,200],"Transformers":[22],"or":[23],"Convolutional":[24],"Neural":[25],"Networks":[26],"(CNNs),":[27],"recent":[28],"diffusion-based":[29],"approaches":[30],"have":[31],"shown":[32],"superior":[33,212],"performance,":[34],"leveraging":[35],"their":[36],"probabilistic":[37],"nature":[38],"high-fidelity":[40],"generation":[41],"capabilities.":[42],"However,":[43],"these":[44,74],"often":[46],"fail":[47],"account":[49],"for":[50],"the":[51,101,116,143,175],"spatial":[52,185],"temporal":[54,62,104,189,215],"correlations":[55],"across":[56],"predicted":[57,68,129],"frames,":[58],"resulting":[59],"in":[60,67,178,217],"limited":[61],"consistency":[63,216],"inferior":[65],"accuracy":[66,102,213],"sequences.":[71],"To":[72],"address":[73],"shortcomings,":[75],"this":[76],"paper":[77],"proposes":[78],"<italic":[79,112,205],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[80,113,206],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">StarPose</i>,":[81],"an":[82,121,179],"autoregressive":[83,122],"diffusion":[84,123],"framework":[85,144],"that":[86,152,204],"effectively":[87],"incorporates":[88],"historical":[89,149],"predictions":[92],"spatial-temporal":[94],"physical":[95],"guidance":[96],"significantly":[98],"enhance":[99],"both":[100],"coherence":[105],"of":[106],"predictions.":[108,160],"Unlike":[109],"existing":[110],"approaches,":[111],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">StarPose</i>":[114,207],"models":[115],"2D-to-3D":[117],"mapping":[119],"as":[120],"process.":[124],"By":[125],"synergically":[126],"integrating":[127],"previously":[128],"poses":[131],"with":[132],"2D":[133],"inputs":[135],"via":[136],"Historical":[138],"Pose":[139],"Integration":[140],"Module":[141],"(HPIM),":[142],"generates":[145],"rich":[146],"informative":[148],"embeddings":[151],"guide":[153],"subsequent":[154],"denoising":[155,176],"steps,":[156],"ensuring":[157],"temporally":[158],"consistent":[159],"In":[161],"addition,":[162],"fully":[164],"plug-and-play":[165],"Spatial-Temporal":[166],"Physical":[167],"Guidance":[168],"(STPG)":[169],"mechanism":[170],"is":[171,223],"tailored":[172],"refine":[174],"process":[177],"iterative":[180],"manner,":[181],"which":[182],"further":[183],"enforces":[184],"anatomical":[186],"plausibility":[187],"motion":[190],"dynamics,":[191],"rendering":[192],"robust":[193],"realistic":[195],"estimates.":[197],"Extensive":[198],"experiments":[199],"benchmark":[201],"datasets":[202],"demonstrate":[203],"outperforms":[208],"state-of-the-art":[209],"methods,":[210],"achieving":[211],"estimation.":[221],"Code":[222],"available":[224],"at":[225],"https://github.com/wileychan/StarPose.":[226]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}