{"id":"https://openalex.org/W4416249474","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227424","title":"HDTPose: A Hierarchical Decoding Transformer for End-to-End Single-Stage Multi-Person Pose Estimation","display_name":"HDTPose: A Hierarchical Decoding Transformer for End-to-End Single-Stage Multi-Person Pose Estimation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249474","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227424"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5101669641","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-1768-8417"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035135129","display_name":"Bin Xue","orcid":"https://orcid.org/0000-0002-2356-8833"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Xue","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368352","display_name":"Qi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Li","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055505703","display_name":"Zhenan Sun","orcid":"https://orcid.org/0000-0003-4029-9935"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenan Sun","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101669641"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34232843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9742000102996826,"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":0.9742000102996826,"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/T12290","display_name":"Human Motion and Animation","score":0.006200000178068876,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.00430000014603138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.7753000259399414},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7681999802589417},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5537999868392944},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46000000834465027},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44830000400543213},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44290000200271606},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42829999327659607},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.38609999418258667}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7753000259399414},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7681999802589417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689300000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5819000005722046},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44290000200271606},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.3070000112056732},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.2930000126361847},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W102499664","https://openalex.org/W2080873731","https://openalex.org/W2194775991","https://openalex.org/W2200124539","https://openalex.org/W2307770531","https://openalex.org/W2559085405","https://openalex.org/W2895457201","https://openalex.org/W2916798096","https://openalex.org/W2952122856","https://openalex.org/W2962773068","https://openalex.org/W2962820842","https://openalex.org/W2963150697","https://openalex.org/W2963402313","https://openalex.org/W2963781481","https://openalex.org/W2964221239","https://openalex.org/W2988916019","https://openalex.org/W2993728126","https://openalex.org/W3012573144","https://openalex.org/W3034399482","https://openalex.org/W3092663126","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3109769043","https://openalex.org/W3166539425","https://openalex.org/W3172013121","https://openalex.org/W3173964191","https://openalex.org/W3176892444","https://openalex.org/W3203003533","https://openalex.org/W3205307530","https://openalex.org/W4221153186","https://openalex.org/W4312967365","https://openalex.org/W4313160152","https://openalex.org/W4398226154","https://openalex.org/W4400527220","https://openalex.org/W4402353526"],"related_works":[],"abstract_inverted_index":{"The":[0,97],"estimation":[1,65,77],"performance":[2],"of":[3,101,156],"human":[4],"keypoints":[5],"varies":[6],"significantly":[7],"across":[8],"different":[9],"keypoint":[10],"types.":[11],"Compared":[12],"to":[13,89,131],"prominent":[14],"joints":[15,27,42,92],"such":[16],"as":[17,78],"the":[18,45,138,152],"head":[19],"and":[20,23,33,48,84,107,115,140,154],"shoulders,":[21],"smaller":[22],"more":[24],"flexible":[25],"limb":[26],"present":[28],"greater":[29],"challenges":[30],"in":[31,93],"identification":[32],"localization.":[34],"Current":[35],"single-stage":[36,149],"methods":[37],"typically":[38],"treat":[39],"all":[40],"body":[41],"uniformly,":[43],"overlooking":[44],"inherent":[46],"differences":[47],"structural":[49],"relationships":[50,130],"among":[51],"keypoints.":[52],"To":[53],"address":[54],"this":[55],"limitation,":[56],"we":[57,120],"propose":[58],"HDTPose,":[59],"a":[60,69,79,86,108,122],"fully":[61],"end-to-end":[62,95],"multi-person":[63,75],"pose":[64,76,133],"framework":[66],"based":[67],"on":[68,137],"hierarchical":[70,80,87],"decoding":[71,98],"transformer.":[72],"HDTPose":[73,145],"formulates":[74],"set":[81],"prediction":[82],"problem":[83],"employs":[85],"decoder":[88],"progressively":[90],"decode":[91],"an":[94,104],"manner.":[96],"process":[99],"consists":[100],"two":[102],"stages:":[103],"instance-aware":[105],"stage":[106],"joint-aware":[109],"stage,":[110],"which":[111],"explicitly":[112],"model":[113],"instance-wise":[114],"joint-wise":[116],"relationships,":[117],"respectively.":[118],"Additionally,":[119],"introduce":[121],"structure-guided":[123],"joint":[124],"attention":[125],"mechanism":[126],"that":[127,144],"leverages":[128],"kinematic":[129],"refine":[132],"predictions.":[134],"Extensive":[135],"experiments":[136],"COCO":[139],"MPII":[141],"benchmarks":[142],"demonstrate":[143],"outperforms":[146],"existing":[147],"state-of-the-art":[148],"methods,":[150],"underscoring":[151],"effectiveness":[153],"superiority":[155],"our":[157],"approach.":[158]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}