{"id":"https://openalex.org/W4391307592","doi":"https://doi.org/10.1109/smc53992.2023.10394434","title":"KTPose: Keypoint-Based Tokens in Vision Transformer for Human Pose Estimation","display_name":"KTPose: Keypoint-Based Tokens in Vision Transformer for Human Pose Estimation","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4391307592","doi":"https://doi.org/10.1109/smc53992.2023.10394434"},"language":"en","primary_location":{"id":"doi:10.1109/smc53992.2023.10394434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53992.2023.10394434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5115695326","display_name":"Jiale Wang","orcid":"https://orcid.org/0009-0006-3817-6644"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Wang","raw_affiliation_strings":["School of Computer Science and Technology, Qingdao University,Qingdao,China,266071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Qingdao University,Qingdao,China,266071","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100655528","display_name":"Wenjia Wang","orcid":"https://orcid.org/0000-0002-1967-0405"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjia Wang","raw_affiliation_strings":["School of Computer Science and Technology, Qingdao University,Qingdao,China,266071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Qingdao University,Qingdao,China,266071","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073521712","display_name":"Xiaowei Zhang","orcid":"https://orcid.org/0000-0003-4854-3736"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Qingdao University,Qingdao,China,266071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Qingdao University,Qingdao,China,266071","institution_ids":["https://openalex.org/I143413998"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143413998"],"apc_list":null,"apc_paid":null,"fwci":0.2428,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61357096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"323","last_page":"328"},"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":0.9934999942779541,"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/T11227","display_name":"Diabetic Foot Ulcer Assessment and Management","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7312521934509277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7297263145446777},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.7276047468185425},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6500451564788818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.616140604019165},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.478497177362442},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4324083626270294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3321007490158081},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09194695949554443},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08100637793540955}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7312521934509277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7297263145446777},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7276047468185425},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6500451564788818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.616140604019165},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.478497177362442},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4324083626270294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3321007490158081},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09194695949554443},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08100637793540955},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53992.2023.10394434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53992.2023.10394434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2977801391","display_name":null,"funder_award_id":"61902204","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":32,"referenced_works":["https://openalex.org/W2013640163","https://openalex.org/W2080873731","https://openalex.org/W2113325037","https://openalex.org/W2307770531","https://openalex.org/W2559085405","https://openalex.org/W2578797046","https://openalex.org/W2776685160","https://openalex.org/W2916798096","https://openalex.org/W2952122856","https://openalex.org/W2963402313","https://openalex.org/W2963598138","https://openalex.org/W2963781481","https://openalex.org/W2964221239","https://openalex.org/W3034399482","https://openalex.org/W3034750257","https://openalex.org/W3108572544","https://openalex.org/W3153807375","https://openalex.org/W3176892444","https://openalex.org/W3203925315","https://openalex.org/W3206810688","https://openalex.org/W4214508443","https://openalex.org/W4224992933","https://openalex.org/W4283813470","https://openalex.org/W4312849330","https://openalex.org/W4312914534","https://openalex.org/W4313127332","https://openalex.org/W4313349624","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6796494063","https://openalex.org/W6802010497","https://openalex.org/W6809664228"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2082783427","https://openalex.org/W4304700937"],"abstract_inverted_index":{"Transformers":[0],"have":[1],"made":[2],"remarkable":[3],"progress":[4],"on":[5,76,118,136],"human":[6,26,42,110],"pose":[7,43,111],"estimation":[8],"in":[9,17,38,88],"recent":[10],"years,":[11],"however,":[12],"vision":[13,86,107],"tokens":[14,37],"are":[15,115],"all":[16],"a":[18,21,34,52,96,147],"fixed":[19],"position,":[20],"property":[22],"unsuitable":[23],"for":[24,41,109],"unknown":[25],"deformation.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,82],"propose":[32,83],"KTPose,":[33],"novel":[35],"keypoint-based":[36],"Vision":[39],"Transformer":[40],"estimation,":[44],"which":[45,89,122],"includes":[46],"an":[47],"instance-aware":[48,64],"keypoint":[49,53,65,91],"head":[50,66],"and":[51,103,129,133,139],"refinement":[54],"with":[55,146],"transformer.":[56],"To":[57],"address":[58],"the":[59,63,71,77,84,154],"limb":[60],"deformation":[61],"issue,":[62],"is":[67,92,144,160],"devised":[68],"to":[69,98,153],"capture":[70],"discriminative":[72],"features":[73],"dynamically":[74],"based":[75],"coarse":[78],"localized":[79],"keypoints.":[80],"Further,":[81],"multi-granularity":[85],"tokens,":[87],"each":[90],"explicitly":[93],"embedded":[94],"as":[95],"token":[97],"simultaneously":[99],"learn":[100],"spatial":[101],"dependencies":[102],"constraint":[104],"relationships":[105],"from":[106],"transformer":[108],"estimation.":[112],"Extensive":[113],"experiments":[114],"carried":[116],"out":[117],"two":[119],"benchmark":[120],"datasets,":[121],"demonstrate":[123],"that":[124],"KTPose":[125],"outperforms":[126],"state-of-the-art":[127],"methods":[128],"achieves":[130],"76.6AP":[131],"(?1.06%)":[132],"75.7AP":[134],"(?0.93%)":[135],"COCO":[137],"validation":[138],"test-dev":[140],"sets,":[141],"respectively.":[142],"This":[143],"accomplished":[145],"smaller":[148],"computational":[149],"footprint":[150],"when":[151],"compared":[152],"current":[155],"mainstream":[156],"transformer-based":[157],"methods.":[158],"Code":[159],"publicly":[161],"available11https://github.com/WINGS-999/KTPose.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}