{"id":"https://openalex.org/W4402915796","doi":"https://doi.org/10.1109/icip51287.2024.10648233","title":"Dtpose: Learning Disentangled Token Representation For Effective Human Pose Estimation","display_name":"Dtpose: Learning Disentangled Token Representation For Effective Human Pose Estimation","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915796","doi":"https://doi.org/10.1109/icip51287.2024.10648233"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10648233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10648233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","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/A5020240417","display_name":"Shiyang Ye","orcid":"https://orcid.org/0000-0003-2943-6249"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyang Ye","raw_affiliation_strings":["Sichuan University,College of Computer Science,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,Chengdu,China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055103025","display_name":"Yuan Fang","orcid":"https://orcid.org/0000-0002-4265-5289"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Fang","raw_affiliation_strings":["Sichuan University,National Key Laboratory of Fundamental Science on Synthetic Vision,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University,National Key Laboratory of Fundamental Science on Synthetic Vision,Chengdu,China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410286","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-0896-8409"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Sichuan University,National Key Laboratory of Fundamental Science on Synthetic Vision,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University,National Key Laboratory of Fundamental Science on Synthetic Vision,Chengdu,China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357677","display_name":"Hu Chen","orcid":"https://orcid.org/0000-0001-9300-6572"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu Chen","raw_affiliation_strings":["Sichuan University,College of Computer Science,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,Chengdu,China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114950325","display_name":"Wenchao Du","orcid":"https://orcid.org/0000-0001-9237-7048"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenchao Du","raw_affiliation_strings":["Sichuan University,College of Computer Science,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,Chengdu,China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103065463","display_name":"Hongyu Yang","orcid":"https://orcid.org/0000-0002-2322-0538"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Yang","raw_affiliation_strings":["Sichuan University,College of Computer Science,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,Chengdu,China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1336","last_page":"1342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9945999979972839,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9896000027656555,"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/security-token","display_name":"Security token","score":0.7782764434814453},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6741124987602234},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6694179773330688},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.6131641864776611},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5447503328323364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5110334157943726},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09115350246429443},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08309298753738403}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7782764434814453},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6741124987602234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6694179773330688},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6131641864776611},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5447503328323364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5110334157943726},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09115350246429443},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08309298753738403},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10648233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10648233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322990","display_name":"Sichuan University","ror":"https://ror.org/011ashp19"},{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2563154851","https://openalex.org/W2916798096","https://openalex.org/W2952122856","https://openalex.org/W2963402313","https://openalex.org/W3136525061","https://openalex.org/W3172976738","https://openalex.org/W3175199633","https://openalex.org/W3203925315","https://openalex.org/W4214508443","https://openalex.org/W4283813470","https://openalex.org/W4312614783","https://openalex.org/W4385245566","https://openalex.org/W4393149992","https://openalex.org/W6794073987","https://openalex.org/W6803650990","https://openalex.org/W6809664228","https://openalex.org/W6809995052","https://openalex.org/W6847718667"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W2711238126","https://openalex.org/W2081371633","https://openalex.org/W4308083507","https://openalex.org/W2286009621","https://openalex.org/W2900273708","https://openalex.org/W3103544346","https://openalex.org/W4282941460"],"abstract_inverted_index":{"Exploring":[0],"rich":[1],"visual":[2,38,85,112],"clues":[3,40,113,129],"and":[4,41,65,86,114,123,127,174,185],"spatial":[5],"geometric":[6,42,148],"constraints":[7,116],"to":[8,36,51,60,81,110,130,143],"locate":[9],"keypoints":[10,152],"is":[11,30,49,108,141],"essential":[12],"for":[13,89],"human":[14],"pose":[15,54],"estimation.":[16],"Existing":[17],"Transformer-based":[18],"methods":[19],"have":[20],"presented":[21],"unique":[22],"advantages":[23],"via":[24,56],"token":[25,35],"representation,":[26],"where":[27],"each":[28],"keypoint":[29,87],"explicitly":[31],"embedded":[32],"as":[33,153,155],"a":[34,73],"learn":[37,52],"appearance":[39,128],"relationships":[43],"simultaneously":[44],"from":[45],"images.":[46],"However,":[47],"it":[48],"difficult":[50],"powerful":[53],"representation":[55,80],"self-attention":[57],"mechanism":[58],"due":[59],"latent":[61],"interference,":[62],"e.g.,":[63],"blurring":[64],"self-occlusion.":[66],"To":[67],"alleviate":[68],"this":[69],"challenge,":[70],"we":[71],"present":[72],"novel":[74],"framework":[75],"that":[76],"Disentangles":[77],"hybrid":[78],"Token":[79,105],"explore":[82,111],"more":[83,133],"effective":[84],"information":[88,150],"Pose":[90],"estimation":[91],"(termed":[92],"by":[93],"DTPose).":[94],"In":[95],"detail,":[96],"DTPose":[97],"contains":[98],"two":[99],"key":[100],"modules.":[101],"First,":[102],"the":[103,120,125,136,145,179,182],"Disentangled":[104],"Representation":[106],"module":[107],"used":[109],"geometry":[115,126],"sequentially,":[117],"which":[118,169],"alleviates":[119],"noise":[121],"interference":[122],"enables":[124],"be":[131],"exploited":[132,142],"sufficiently.":[134],"Furthermore,":[135],"Hierarchical":[137],"Spatial":[138],"Decoding":[139],"head":[140],"preserve":[144],"2":[146],"D":[147],"structure":[149],"of":[151,166],"much":[154],"possible.":[156],"Extensive":[157],"experiments":[158],"on":[159,181],"COCO":[160,183],"dataset":[161],"demonstrate":[162],"significant":[163],"performance":[164],"gains":[165],"our":[167],"DTPose,":[168],"achieves":[170],"76.5":[171],"(+0.7)":[172],"AP":[173,177],"75.7":[175],"(+0.6)":[176],"than":[178],"TokenPose-L":[180],"validation":[184],"test-dev":[186],"sets":[187],"separately.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}