{"id":"https://openalex.org/W4393021428","doi":"https://doi.org/10.1007/s40747-024-01361-y","title":"GITPose: going shallow and deeper using vision transformers for human pose estimation","display_name":"GITPose: going shallow and deeper using vision transformers for human pose estimation","publication_year":2024,"publication_date":"2024-03-20","ids":{"openalex":"https://openalex.org/W4393021428","doi":"https://doi.org/10.1007/s40747-024-01361-y"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-024-01361-y","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s40747-024-01361-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01361-y.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01361-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035217566","display_name":"Evans Aidoo","orcid":"https://orcid.org/0000-0002-8682-8022"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Evans Aidoo","raw_affiliation_strings":["School of statistics and mathematics, Zhejiang Gongsheng University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8682-8022","affiliations":[{"raw_affiliation_string":"School of statistics and mathematics, Zhejiang Gongsheng University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333854","display_name":"Xun Wang","orcid":"https://orcid.org/0000-0002-2741-433X"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Wang","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101715620","display_name":"Zhenguang Liu","orcid":"https://orcid.org/0000-0002-7981-9873"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenguang Liu","raw_affiliation_strings":["School of Cyber Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043508925","display_name":"Abraham Opanfo Abbam","orcid":null},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Abraham Opanfo Abbam","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065387302","display_name":"Edwin Kwadwo Tenagyei","orcid":null},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Edwin Kwadwo Tenagyei","raw_affiliation_strings":["School of Engineering and Built Environment, Griffith University, Nathan, QLD, 4111, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering and Built Environment, Griffith University, Nathan, QLD, 4111, Australia","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039845163","display_name":"Victor Nonso Ejianya","orcid":"https://orcid.org/0000-0001-7717-4912"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Victor Nonso Ejianya","raw_affiliation_strings":["School of statistics and mathematics, Zhejiang Gongsheng University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of statistics and mathematics, Zhejiang Gongsheng University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012183652","display_name":"Seth Larweh Kodjiku","orcid":"https://orcid.org/0000-0003-2871-5860"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Seth Larweh Kodjiku","raw_affiliation_strings":["School of statistics and mathematics, Zhejiang Gongsheng University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of statistics and mathematics, Zhejiang Gongsheng University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022953025","display_name":"Esther Stacy E. B. Aggrey","orcid":"https://orcid.org/0000-0002-1657-7774"},"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":"Esther Stacy E. B. Aggrey","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, 610054, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, 610054, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5035217566"],"corresponding_institution_ids":["https://openalex.org/I75059550"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.2381,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45643311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"10","issue":"3","first_page":"4507","last_page":"4520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.6824651956558228},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.581377387046814},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5586578249931335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5131533741950989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5011191368103027},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49312326312065125},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4200665354728699},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3031635880470276},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13783591985702515},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.11847469210624695},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05083027482032776}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.6824651956558228},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.581377387046814},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5586578249931335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131533741950989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5011191368103027},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49312326312065125},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4200665354728699},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3031635880470276},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13783591985702515},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.11847469210624695},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05083027482032776}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-024-01361-y","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s40747-024-01361-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01361-y.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:989418b1240b4c0eba690008593a23a8","is_oa":true,"landing_page_url":"https://doaj.org/article/989418b1240b4c0eba690008593a23a8","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 10, Iss 3, Pp 4507-4520 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-024-01361-y","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s40747-024-01361-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01361-y.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4548882678","display_name":null,"funder_award_id":"LZ23F020004","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320312301","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4393021428.pdf"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1936750108","https://openalex.org/W2080873731","https://openalex.org/W2108598243","https://openalex.org/W2113325037","https://openalex.org/W2307770531","https://openalex.org/W2565639579","https://openalex.org/W2578797046","https://openalex.org/W2585123518","https://openalex.org/W2601564443","https://openalex.org/W2795580403","https://openalex.org/W2916798096","https://openalex.org/W2962773068","https://openalex.org/W2962820842","https://openalex.org/W2962843773","https://openalex.org/W2963402313","https://openalex.org/W2963598138","https://openalex.org/W2964221239","https://openalex.org/W2964304707","https://openalex.org/W2979826702","https://openalex.org/W3034399482","https://openalex.org/W3034742259","https://openalex.org/W3034750257","https://openalex.org/W3094502228","https://openalex.org/W3095753995","https://openalex.org/W3096609285","https://openalex.org/W3108651438","https://openalex.org/W3109579921","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3142589538","https://openalex.org/W3158758286","https://openalex.org/W3171953676","https://openalex.org/W3173415456","https://openalex.org/W3175199633","https://openalex.org/W3178774897","https://openalex.org/W3203925315","https://openalex.org/W4214493665","https://openalex.org/W4214508443","https://openalex.org/W4214634256","https://openalex.org/W4221163763","https://openalex.org/W4285300683","https://openalex.org/W4295214911","https://openalex.org/W4312305353","https://openalex.org/W4312614783","https://openalex.org/W4312914534","https://openalex.org/W4313156423","https://openalex.org/W4392797103","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W2894986065","https://openalex.org/W4387967917","https://openalex.org/W4287600488","https://openalex.org/W4386925306","https://openalex.org/W4387968151","https://openalex.org/W2736638679","https://openalex.org/W4313046826","https://openalex.org/W1968716783"],"abstract_inverted_index":{"Abstract":[0],"In":[1,101,148],"comparison":[2],"to":[3,34,42,65,114,132,159,191],"convolutional":[4],"neural":[5],"networks":[6],"(CNN),":[7],"the":[8,39,49,53,66,116,122,137,172],"newly":[9],"created":[10],"vision":[11],"transformer":[12,54,107],"(ViT)":[13],"has":[14],"demonstrated":[15],"impressive":[16],"outcomes":[17],"in":[18,30,108,121,136],"human":[19,90],"pose":[20,188],"estimation":[21,93,189],"(HPE).":[22],"However,":[23],"(1)":[24],"there":[25],"is":[26],"a":[27,76,105,143,152,182],"quadratic":[28],"rise":[29],"complexity":[31],"with":[32,83],"respect":[33],"image":[35],"size,":[36],"which":[37,109],"causes":[38],"traditional":[40],"ViT":[41],"be":[43],"unsuitable":[44],"for":[45,89,98,145],"scaling,":[46],"and":[47,81,142,161,169,174],"(2)":[48],"attention":[50],"process":[51],"at":[52],"encoder":[55],"as":[56,58],"well":[57],"decoder":[59,144],"also":[60],"adds":[61],"substantial":[62],"computational":[63],"costs":[64],"detector\u2019s":[67],"overall":[68],"processing":[69],"time.":[70],"Motivated":[71],"by":[72],"this,":[73],"we":[74,103,110,150],"propose":[75],"novel":[77],"G":[78],"oing":[79],"shallow":[80],"deeper":[82,138],"v":[84],"I":[85],"sion":[86],"T":[87],"ransformers":[88],"P":[91],"ose":[92],"(GITPose)":[94],"without":[95],"CNN":[96],"backbones":[97],"feature":[99,119],"extraction.":[100],"particular,":[102],"introduce":[104],"hierarchical":[106],"utilize":[111],"multilayer":[112],"perceptrons":[113],"encode":[115,133],"richest":[117],"local":[118],"tokens":[120],"initial":[123],"phases":[124],"(i.e.,":[125,140],"shallow),":[126],"whereas":[127],"self-attention":[128],"modules":[129],"are":[130],"employed":[131],"long-term":[134],"relationships":[135],"layers":[139],"deeper),":[141],"keypoint":[146,165],"detection.":[147],"addition,":[149],"offer":[151],"learnable":[153],"deformable":[154],"token":[155],"association":[156],"module":[157],"(DTA)":[158],"non-uniformly":[160],"dynamically":[162],"combine":[163],"informative":[164],"tokens.":[166],"Comprehensive":[167],"evaluation":[168],"testing":[170],"on":[171,187],"COCO":[173],"MPII":[175],"benchmark":[176],"datasets":[177],"reveal":[178],"that":[179],"GITPose":[180],"achieves":[181],"competitive":[183],"average":[184],"precision":[185],"(AP)":[186],"compared":[190],"its":[192],"state-of-the-art":[193],"approaches.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-01-23T23:20:30.427331","created_date":"2025-10-10T00:00:00"}