{"id":"https://openalex.org/W4388284323","doi":"https://doi.org/10.1109/tpami.2023.3330016","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","display_name":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","publication_year":2023,"publication_date":"2023-11-03","ids":{"openalex":"https://openalex.org/W4388284323","doi":"https://doi.org/10.1109/tpami.2023.3330016","pmid":"https://pubmed.ncbi.nlm.nih.gov/37922160"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3330016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3330016","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/A5042154277","display_name":"Yufei Xu","orcid":"https://orcid.org/0000-0002-9931-5138"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yufei Xu","raw_affiliation_strings":["Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9931-5138","affiliations":[{"raw_affiliation_string":"Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345321","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-6595-7661"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6595-7661","affiliations":[{"raw_affiliation_string":"Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639013","display_name":"Qiming Zhang","orcid":"https://orcid.org/0000-0003-0060-0543"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiming Zhang","raw_affiliation_strings":["Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0060-0543","affiliations":[{"raw_affiliation_string":"Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":11.2626,"has_fulltext":false,"cited_by_count":118,"citation_normalized_percentile":{"value":0.99281586,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"46","issue":"2","first_page":"1212","last_page":"1230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.7819878458976746},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6431178450584412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.63510662317276},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6025072336196899},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5495194792747498},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.489241361618042},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45772063732147217},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43714267015457153},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3981534540653229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819878458976746},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6431178450584412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.63510662317276},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6025072336196899},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5495194792747498},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.489241361618042},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45772063732147217},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43714267015457153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3981534540653229},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3330016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3330016","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:37922160","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37922160","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7519899501","display_name":null,"funder_award_id":"FL-170100117","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W2080873731","https://openalex.org/W2108598243","https://openalex.org/W2113325037","https://openalex.org/W2175012183","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2382036597","https://openalex.org/W2476548250","https://openalex.org/W2578797046","https://openalex.org/W2612947062","https://openalex.org/W2768477045","https://openalex.org/W2792643794","https://openalex.org/W2916431757","https://openalex.org/W2916798096","https://openalex.org/W2958537753","https://openalex.org/W2962730651","https://openalex.org/W2962820842","https://openalex.org/W2962954622","https://openalex.org/W2963402313","https://openalex.org/W2963781481","https://openalex.org/W2964221239","https://openalex.org/W2993728126","https://openalex.org/W3020589396","https://openalex.org/W3034368386","https://openalex.org/W3034399482","https://openalex.org/W3034742259","https://openalex.org/W3034750257","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3107825842","https://openalex.org/W3108418701","https://openalex.org/W3108651438","https://openalex.org/W3109340983","https://openalex.org/W3110017807","https://openalex.org/W3110103163","https://openalex.org/W3113950706","https://openalex.org/W3131500599","https://openalex.org/W3138154797","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3176892444","https://openalex.org/W3178774897","https://openalex.org/W3185341429","https://openalex.org/W3187458216","https://openalex.org/W3195577433","https://openalex.org/W3196660197","https://openalex.org/W3203925315","https://openalex.org/W3215626407","https://openalex.org/W4214508443","https://openalex.org/W4214893857","https://openalex.org/W4221142320","https://openalex.org/W4229911490","https://openalex.org/W4242788899","https://openalex.org/W4285247752","https://openalex.org/W4289047567","https://openalex.org/W4309611266","https://openalex.org/W4312257978","https://openalex.org/W4312446817","https://openalex.org/W4312769131","https://openalex.org/W4312799843","https://openalex.org/W4312914534","https://openalex.org/W4313069532","https://openalex.org/W4313156423","https://openalex.org/W4315705623","https://openalex.org/W4383755718","https://openalex.org/W4386065386","https://openalex.org/W4389977645","https://openalex.org/W6638523607","https://openalex.org/W6730410022","https://openalex.org/W6732520560","https://openalex.org/W6747620207","https://openalex.org/W6749029207","https://openalex.org/W6757733370","https://openalex.org/W6759892625","https://openalex.org/W6788135285","https://openalex.org/W6790935598","https://openalex.org/W6795140394","https://openalex.org/W6796761347","https://openalex.org/W6797235774","https://openalex.org/W6800751262","https://openalex.org/W6800922194","https://openalex.org/W6802010497","https://openalex.org/W6803872405","https://openalex.org/W6809664228","https://openalex.org/W6810334672","https://openalex.org/W6810615099","https://openalex.org/W6838745215","https://openalex.org/W6838906284","https://openalex.org/W6846529796"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W4390516098","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"show":[4],"the":[5,48,85,88,110,122,148,154,182],"surprisingly":[6],"good":[7],"properties":[8],"of":[9,35,87,156,201],"plain":[10,49],"vision":[11,52],"transformers":[12],"for":[13,100,213,218,228],"body":[14,66,134,202],"pose":[15,203],"estimation":[16,204],"from":[17],"various":[18],"aspects,":[19],"namely":[20],"simplicity":[21],"in":[22,26,30,68,147],"model":[23,27,43,90,127,175,188,193],"structure,":[24],"scalability":[25],"size,":[28],"flexibility":[29],"training":[31],"paradigm,":[32],"and":[33,50,60,92,102,115,117,143,226],"transferability":[34],"knowledge":[36,138,155,170],"between":[37],"models,":[38],"through":[39],"a":[40,61,70,73,96,124,168,178,199],"simple":[41,169],"baseline":[42],"dubbed":[44],"ViTPose.":[45],"ViTPose":[46,105,158],"employs":[47],"non-hierarchical":[51],"transformer":[53],"as":[54,222,224],"an":[55],"encoder":[56],"to":[57,64,80,130,164],"encode":[58],"features":[59],"lightweight":[62],"decoder":[63],"decode":[65],"keypoints":[67],"either":[69],"top-down":[71],"or":[72],"bottom-up":[74],"manner.":[75],"It":[76],"can":[77,160],"be":[78,161],"scaled":[79],"1B":[81],"parameters":[82],"by":[83],"taking":[84],"advantage":[86],"scalable":[89],"capacity":[91],"high":[93],"parallelism,":[94],"setting":[95],"new":[97,179],"Pareto":[98],"front":[99],"throughput":[101],"performance.":[103],"Besides,":[104],"is":[106,128],"very":[107],"flexible":[108],"regarding":[109],"attention":[111],"type,":[112],"input":[113],"resolution,":[114],"pre-training":[116],"fine-tuning":[118],"strategy.":[119],"Based":[120],"on":[121,181,198],"flexibility,":[123],"novel":[125],"ViTPose++":[126,192],"proposed":[129],"deal":[131],"with":[132],"heterogeneous":[133],"keypoint":[135,215,220,230],"categories":[136],"via":[137,167],"factorization,":[139],"i.e.,":[140],"adopting":[141],"task-agnostic":[142],"task-specific":[144],"feed-forward":[145],"networks":[146],"transformer.":[149],"We":[150],"also":[151],"demonstrate":[152],"that":[153],"large":[157],"models":[159],"easily":[162],"transferred":[163],"small":[165],"ones":[166],"token.":[171],"Our":[172],"largest":[173],"single":[174],"ViTPose-G":[176],"sets":[177],"record":[180],"MS":[183,207],"COCO":[184],"test":[185],"set":[186],"without":[187,232],"ensemble.":[189],"Furthermore,":[190],"our":[191],"achieves":[194],"state-of-the-art":[195],"performance":[196],"simultaneously":[197],"series":[200],"tasks,":[205],"including":[206],"COCO,":[208],"AI":[209],"Challenger,":[210],"OCHuman,":[211],"MPII":[212],"human":[214],"detection,":[216,221,231],"COCO-Wholebody":[217],"whole-body":[219],"well":[223],"AP-10K":[225],"APT-36K":[227],"animal":[229],"sacrificing":[233],"inference":[234],"speed.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":34},{"year":2025,"cited_by_count":55},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}