{"id":"https://openalex.org/W3203925315","doi":"https://doi.org/10.1109/iccv48922.2021.01112","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","display_name":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W3203925315","doi":"https://doi.org/10.1109/iccv48922.2021.01112","mag":"3203925315"},"language":"en","primary_location":{"id":"doi:10.1109/iccv48922.2021.01112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv48922.2021.01112","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-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/A5100677181","display_name":"Yanjie Li","orcid":"https://orcid.org/0000-0002-4074-5109"},"institutions":[{"id":"https://openalex.org/I4210109870","display_name":"Vi Technology (United States)","ror":"https://ror.org/016mnbp44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109870"]},{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Yanjie Li","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School","MEGVII Technology","Tsinghua Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"MEGVII Technology","institution_ids":["https://openalex.org/I4210109870","https://openalex.org/I4401726805"]},{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021064156","display_name":"Shoukui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109870","display_name":"Vi Technology (United States)","ror":"https://ror.org/016mnbp44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109870"]},{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shoukui Zhang","raw_affiliation_strings":["MEGVII Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MEGVII Technology","institution_ids":["https://openalex.org/I4210109870","https://openalex.org/I4401726805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429162","display_name":"Zhicheng Wang","orcid":"https://orcid.org/0000-0001-5444-6671"},"institutions":[{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]},{"id":"https://openalex.org/I4210109870","display_name":"Vi Technology (United States)","ror":"https://ror.org/016mnbp44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhicheng Wang","raw_affiliation_strings":["MEGVII Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MEGVII Technology","institution_ids":["https://openalex.org/I4210109870","https://openalex.org/I4401726805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002854172","display_name":"Sen Yang","orcid":"https://orcid.org/0000-0003-3222-2268"},"institutions":[{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]},{"id":"https://openalex.org/I4210109870","display_name":"Vi Technology (United States)","ror":"https://ror.org/016mnbp44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sen Yang","raw_affiliation_strings":["MEGVII Technology","Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MEGVII Technology","institution_ids":["https://openalex.org/I4210109870","https://openalex.org/I4401726805"]},{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748706","display_name":"Wankou Yang","orcid":"https://orcid.org/0000-0002-6385-6776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wankou Yang","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034104790","display_name":"Shu\u2010Tao Xia","orcid":"https://orcid.org/0000-0002-8639-982X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu-Tao Xia","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School","Tsinghua Shenzhen International Graduate School, Tsinghua University","PCL Research Center of Networks and Communications, Peng Cheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"PCL Research Center of Networks and Communications, Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060050139","display_name":"Erjin Zhou","orcid":"https://orcid.org/0000-0001-9234-0026"},"institutions":[{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]},{"id":"https://openalex.org/I4210109870","display_name":"Vi Technology (United States)","ror":"https://ror.org/016mnbp44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erjin Zhou","raw_affiliation_strings":["MEGVII Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MEGVII Technology","institution_ids":["https://openalex.org/I4210109870","https://openalex.org/I4401726805"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100677181"],"corresponding_institution_ids":["https://openalex.org/I4210109870","https://openalex.org/I4210114105","https://openalex.org/I4401726805","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":15.5587,"has_fulltext":false,"cited_by_count":370,"citation_normalized_percentile":{"value":0.99426934,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11293","last_page":"11302"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9984999895095825,"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":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.818556010723114},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.7848181128501892},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.7374740242958069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7287513017654419},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6724705100059509},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.6629763245582581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6624903082847595},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6478560566902161},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4376462996006012},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43746674060821533},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43182119727134705},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41747117042541504},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15033528208732605},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07859835028648376}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.818556010723114},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7848181128501892},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.7374740242958069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287513017654419},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6724705100059509},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.6629763245582581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6624903082847595},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6478560566902161},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4376462996006012},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43746674060821533},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43182119727134705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41747117042541504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15033528208732605},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07859835028648376},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv48922.2021.01112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv48922.2021.01112","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309618","display_name":"Ministry of Science and Technology","ror":"https://ror.org/02b207r52"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1861492603","https://openalex.org/W1936750108","https://openalex.org/W2080873731","https://openalex.org/W2147800946","https://openalex.org/W2307770531","https://openalex.org/W2330914857","https://openalex.org/W2375583958","https://openalex.org/W2578797046","https://openalex.org/W2742737904","https://openalex.org/W2889332130","https://openalex.org/W2896457183","https://openalex.org/W2916798096","https://openalex.org/W2952819818","https://openalex.org/W2958088908","https://openalex.org/W2962773068","https://openalex.org/W2963402313","https://openalex.org/W2963448913","https://openalex.org/W2963598138","https://openalex.org/W2963781481","https://openalex.org/W2964221239","https://openalex.org/W2964304707","https://openalex.org/W3034399482","https://openalex.org/W3034750257","https://openalex.org/W3034945237","https://openalex.org/W3034971010","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3113950706","https://openalex.org/W3117707723","https://openalex.org/W3121523901","https://openalex.org/W3122239467","https://openalex.org/W3131500599","https://openalex.org/W3133696297","https://openalex.org/W3136525061","https://openalex.org/W3165924482","https://openalex.org/W3170841864","https://openalex.org/W3170874841","https://openalex.org/W3171125843","https://openalex.org/W3175199633","https://openalex.org/W4287259027","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6636510571","https://openalex.org/W6639102338","https://openalex.org/W6692078629","https://openalex.org/W6697925102","https://openalex.org/W6730410022","https://openalex.org/W6739901393","https://openalex.org/W6745881451","https://openalex.org/W6748709139","https://openalex.org/W6750378959","https://openalex.org/W6755207826","https://openalex.org/W6778485988","https://openalex.org/W6778883912","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6786026227","https://openalex.org/W6786585107","https://openalex.org/W6787248546","https://openalex.org/W6787906798","https://openalex.org/W6788135285","https://openalex.org/W6788620109","https://openalex.org/W6790690058","https://openalex.org/W6791517108"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W3102845713","https://openalex.org/W2971502891","https://openalex.org/W3205506801","https://openalex.org/W4388335561","https://openalex.org/W4280599700","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618"],"abstract_inverted_index":{"Human":[0],"pose":[1],"estimation":[2,53],"deeply":[3],"relies":[4],"on":[5,47,86,107],"visual":[6,23],"clues":[7],"and":[8,70,81,99,104,121],"anatomical":[9],"constraints":[10],"between":[11,36],"parts":[12],"to":[13,30,65],"locate":[14],"keypoints.":[15,37],"Most":[16],"existing":[17],"CNN-based":[18,90],"methods":[19],"do":[20],"well":[21],"in":[22,27,115],"representation,":[24],"however,":[25],"lacking":[26],"the":[28,33,79],"ability":[29],"explicitly":[31,60],"learn":[32,67],"constraint":[34,68],"relationships":[35,69],"In":[38,55],"this":[39],"paper,":[40],"we":[41],"propose":[42],"a":[43,63],"novel":[44],"approach":[45],"based":[46],"Token":[48],"representation":[49],"for":[50],"human":[51],"Pose":[52],"(TokenPose).":[54],"detail,":[56],"each":[57],"keypoint":[58],"is":[59,127],"embedded":[61],"as":[62],"token":[64],"simultaneously":[66],"appearance":[71],"cues":[72],"from":[73],"images.":[74],"Extensive":[75],"experiments":[76],"show":[77],"that":[78],"small":[80],"large":[82],"TokenPose":[83],"models":[84],"are":[85],"par":[87],"with":[88,112],"state-of-the-art":[89],"counterparts":[91],"while":[92],"being":[93],"more":[94],"lightweight.":[95],"Specifically,":[96],"our":[97],"TokenPose-S":[98],"TokenPose-L":[100],"achieve":[101],"72.5":[102],"AP":[103,106],"75.8":[105],"COCO":[108],"validation":[109],"dataset":[110],"respectively,":[111],"significant":[113],"reduction":[114],"parameters":[116],"(\u219380.6%":[117],";":[118],"\u2193":[119],"56.8%)":[120],"GFLOPs":[122],"(\u2193":[123],"75.3%;":[124],"\u219324.7%).":[125],"Code":[126],"publicly":[128],"available":[129],"<sup":[130],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[131],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[132],".":[133]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":110},{"year":2024,"cited_by_count":99},{"year":2023,"cited_by_count":90},{"year":2022,"cited_by_count":44},{"year":2021,"cited_by_count":4}],"updated_date":"2026-05-12T08:28:47.272897","created_date":"2025-10-10T00:00:00"}