{"id":"https://openalex.org/W7123357427","doi":"https://doi.org/10.1109/tpami.2026.3651728","title":"Unleashing the Power of Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation","display_name":"Unleashing the Power of Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123357427","doi":"https://doi.org/10.1109/tpami.2026.3651728","pmid":"https://pubmed.ncbi.nlm.nih.gov/41525596"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3651728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3651728","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5122874144","display_name":"Duo Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Duo Peng","raw_affiliation_strings":["Institute for Digital Molecular Analytics and Science, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3281-0772","affiliations":[{"raw_affiliation_string":"Institute for Digital Molecular Analytics and Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031460813","display_name":"Zhengbo Zhang","orcid":"https://orcid.org/0009-0000-8956-0095"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhengbo Zhang","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ping Hu","orcid":"https://orcid.org/0000-0003-3321-6759"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Hu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0003-3321-6759","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121339040","display_name":"Qiuhong Ke","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiuhong Ke","raw_affiliation_strings":["Monash University, Clayton, Victoria, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9998-3614","affiliations":[{"raw_affiliation_string":"Monash University, Clayton, Victoria, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116167505","display_name":"De Wen Soh","orcid":null},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"De Wen Soh","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6490-6467","affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mohammed Bennamoun","orcid":"https://orcid.org/0000-0002-6603-3257"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammed Bennamoun","raw_affiliation_strings":["University of Western Australia, Crawley, Western Australia, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6603-3257","affiliations":[{"raw_affiliation_string":"University of Western Australia, Crawley, Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-4365-4165"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["Lancaster University, Lancaster, Lancashire, U.K"],"raw_orcid":"https://orcid.org/0000-0002-4365-4165","affiliations":[{"raw_affiliation_string":"Lancaster University, Lancaster, Lancashire, U.K","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05027404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"5","first_page":"5195","last_page":"5211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.39340001344680786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.39340001344680786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.36329999566078186,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.02810000069439411,"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/pose","display_name":"Pose","score":0.7132999897003174},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6599000096321106},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6032999753952026},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5964999794960022},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5533000230789185},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.47600001096725464},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4133000075817108},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.4115000069141388},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3709000051021576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8138999938964844},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7132999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.67330002784729},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6599000096321106},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6032999753952026},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5964999794960022},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.47600001096725464},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.461899995803833},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4133000075817108},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3824999928474426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.366100013256073},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.28060001134872437},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tpami.2026.3651728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3651728","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41525596","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41525596","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:eprints.lancs.ac.uk:237512","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:oai:pure.atira.dk:publications/9c741125-4eb0-4ec6-89ba-75f48fcc6a1d","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/9c741125-4eb0-4ec6-89ba-75f48fcc6a1d","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Peng, D, Zhang, Z, Hu, P, Ke, Q, Soh, D W, Bennamoun, M & Liu, J 2026, 'Unleashing the Power of Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation', IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 48, no. 5, pp. 5195-5211. https://doi.org/10.1109/TPAMI.2026.3651728","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/212544","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/212544","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4209815111","display_name":null,"funder_award_id":"AISG2-PhD-2022-01-027","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G4835685075","display_name":null,"funder_award_id":"62476048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8012255999","display_name":null,"funder_award_id":"EDUNC-33-18-279-V12","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Category-Agnostic":[0],"Pose":[1,33],"Estimation":[2],"(CAPE)":[3],"aims":[4],"to":[5,25,76,97,121,142],"detect":[6],"keypoints":[7,82],"of":[8,19,43,69,81],"unseen":[9],"object":[10],"categories":[11,104],"in":[12,177],"a":[13,36,93,115,133,152,178],"few-shot":[14,55],"setting,":[15],"where":[16],"the":[17,41,58,78,99,109,130],"scarcity":[18],"labeled":[20],"data":[21],"poses":[22],"significant":[23],"challenges":[24],"generalization.":[26],"In":[27],"this":[28],"work,":[29],"we":[30,91,113],"propose":[31,114],"Prompt":[32,153],"Matching":[34],"(PPM),":[35],"novel":[37],"framework":[38,174],"that":[39,165],"unleashes":[40],"power":[42],"off-the-shelf":[44],"text-to-image":[45,59],"diffusion":[46,60],"models":[47],"for":[48,146],"CAPE.":[49],"PPM":[50,173],"learns":[51],"pseudo":[52,64],"prompts":[53,65,87],"from":[54,83],"examples":[56],"via":[57],"model.":[61],"These":[62],"learned":[63],"capture":[66,98],"semantic":[67],"information":[68],"keypoints,":[70],"which":[71],"can":[72,175],"then":[73],"be":[74,187],"used":[75],"locate":[77],"same":[79],"type":[80],"images.":[84],"To":[85,107],"provide":[86,122],"with":[88],"representative":[89],"initialization,":[90],"introduce":[92],"category-agnostic":[94],"pre-training":[95],"strategy":[96],"foreground":[100,131],"prior":[101],"shared":[102],"across":[103],"and":[105,124],"keypoints.":[106],"support":[108],"reliable":[110],"prompt":[111],"pre-training,":[112],"Foreground-Aware":[116],"Region":[117],"Aggregation":[118],"(FARA)":[119],"module":[120,138],"robust":[123],"consistent":[125],"supervision":[126],"signal.":[127],"Based":[128],"on":[129,168],"prior,":[132],"Foreground-Guided":[134],"Attention":[135],"Refinement":[136],"(FGAR)":[137],"is":[139],"further":[140],"proposed":[141],"reinforce":[143],"cross-attention":[144],"responses":[145],"accurate":[147],"keypoint":[148,160],"localization.":[149],"For":[150],"efficiency,":[151],"Ensemble":[154],"Inference":[155],"(PEI)":[156],"scheme":[157],"enables":[158],"joint":[159],"prediction.":[161],"Unlike":[162],"previous":[163],"methods":[164],"highly":[166],"rely":[167],"base-category":[169],"annotated":[170],"data,":[171],"our":[172],"operate":[176],"base-category-free":[179],"setting":[180],"while":[181],"retaining":[182],"strong":[183],"performance.":[184],"Code":[185],"will":[186],"available":[188],"at:":[189],"https://github.com/DuoPeng-CVer/Prompt-Pose-Matching.":[190]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-01-14T00:00:00"}