{"id":"https://openalex.org/W4413553547","doi":"https://doi.org/10.1109/tcsvt.2025.3602066","title":"Hierarchical Contrastive Consistency for Human Pose Estimation in Images and Videos","display_name":"Hierarchical Contrastive Consistency for Human Pose Estimation in Images and Videos","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4413553547","doi":"https://doi.org/10.1109/tcsvt.2025.3602066"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3602066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3602066","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5067613982","display_name":"Xixia Xu","orcid":"https://orcid.org/0000-0001-6305-475X"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xixia Xu","raw_affiliation_strings":["Bio-Vision System Laboratory and the Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, China","Shanghai Institute of Microsystem and Information Technology, Bio-vision System Laboratory, Science and Technology on Micro-system Laboratory, Chinese Academy of Sciences, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6305-475X","affiliations":[{"raw_affiliation_string":"Bio-Vision System Laboratory and the Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210147322"]},{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, Bio-vision System Laboratory, Science and Technology on Micro-system Laboratory, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101696368","display_name":"Qi Zou","orcid":"https://orcid.org/0000-0002-8070-5267"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zou","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","School of Computer and Information Technology, Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8070-5267","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035418350","display_name":"Jiamao Li","orcid":"https://orcid.org/0000-0002-7478-4544"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamao Li","raw_affiliation_strings":["Bio-Vision System Laboratory and the Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, China","Shanghai Institute of Microsystem and Information Technology, Bio-vision System Laboratory, Science and Technology on Micro-system Laboratory, Chinese Academy of Sciences, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7478-4544","affiliations":[{"raw_affiliation_string":"Bio-Vision System Laboratory and the Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210147322"]},{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, Bio-vision System Laboratory, Science and Technology on Micro-system Laboratory, Chinese Academy of Sciences, Shanghai, China","institution_ids":["https://openalex.org/I4210147322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.178588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"2","first_page":"1837","last_page":"1847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9968000054359436,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7029995918273926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6590986251831055},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6335581541061401},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5357242226600647},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4470877945423126},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4270371198654175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7029995918273926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6590986251831055},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6335581541061401},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5357242226600647},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4470877945423126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4270371198654175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3602066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3602066","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2044847244","display_name":null,"funder_award_id":"22XD1424500","funder_id":"https://openalex.org/F4320335796","funder_display_name":"Program of Shanghai Academic Research Leader"},{"id":"https://openalex.org/G237787280","display_name":null,"funder_award_id":"2021ZD0201403","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G5351150603","display_name":null,"funder_award_id":"24ZR1476900","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335796","display_name":"Program of Shanghai Academic Research Leader","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2554082199","https://openalex.org/W2604346130","https://openalex.org/W2897251884","https://openalex.org/W2913824500","https://openalex.org/W2916798096","https://openalex.org/W2956532199","https://openalex.org/W2959975024","https://openalex.org/W2962730651","https://openalex.org/W2963402313","https://openalex.org/W2964084369","https://openalex.org/W3010874390","https://openalex.org/W3020589396","https://openalex.org/W3035435924","https://openalex.org/W3114632476","https://openalex.org/W3168822201","https://openalex.org/W3170837227","https://openalex.org/W3173415456","https://openalex.org/W3175123126","https://openalex.org/W3205032456","https://openalex.org/W4214913425","https://openalex.org/W4226265242","https://openalex.org/W4291926315","https://openalex.org/W4312305353","https://openalex.org/W4312695182","https://openalex.org/W4312762601","https://openalex.org/W4313145071","https://openalex.org/W4313886816","https://openalex.org/W4379985979","https://openalex.org/W4382456802","https://openalex.org/W4386076518","https://openalex.org/W4387587636","https://openalex.org/W4390874241","https://openalex.org/W4402696041","https://openalex.org/W4402753719","https://openalex.org/W4402973642"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Human":[0],"pose":[1],"estimation":[2],"(HPE)":[3],"is":[4,64],"an":[5],"invaluable":[6],"task":[7],"in":[8,29,161,202],"computer":[9],"vision":[10],"with":[11],"various":[12],"practical":[13],"applications.":[14],"This":[15],"paper":[16],"proposes":[17],"a":[18],"novel":[19],"Hierarchical":[20],"Contrastive":[21],"Consistensy":[22],"constraint":[23,152],"(HICCON)":[24],"to":[25,86,102,132,154,163],"improve":[26,103],"the":[27,36,53,88,95,104,111,117,124,146,150,183,192,196,199],"HPE":[28,203],"both":[30],"images":[31],"and":[32,43,46,58,72,79,126,180],"videos,":[33],"which":[34],"describes":[35],"input":[37],"into":[38],"multi-granular":[39],"representations":[40],"at":[41,66],"spatial":[42],"temporal":[44,136,167],"domain":[45],"performs":[47],"multi-level":[48],"feature":[49,98,128],"consistency":[50,81,129],"by":[51],"exploring":[52],"characteristic":[54],"of":[55,173,198],"human":[56],"structure":[57],"time":[59],"sequence.":[60],"The":[61,92,108,138],"hierarchical":[62],"contrast":[63,99],"conducted":[65],"four":[67],"levels:":[68],"keypoint-level,":[69],"part-level,":[70],"instance-level":[71,125],"clip-level.":[73],"In":[74,120],"spatial,":[75],"we":[76,122],"consider":[77],"keypoint-level":[78],"part-level":[80],"across":[82,100,130,143,175],"instances":[83,101],"within":[84,145],"frame":[85],"enhance":[87],"fine-grained":[89],"keypoint":[90,97,106],"robustness.":[91],"former":[93,139],"conducts":[94],"single":[96],"category-specific":[105],"features.":[107,168],"latter":[109],"explores":[110],"specific":[112],"pair-wise":[113],"features":[114,142,157],"for":[115],"preserving":[116],"instructive":[118],"relation.":[119],"temporal,":[121],"develop":[123],"clip-level":[127,151],"frames":[131,144],"capture":[133,164],"more":[134,165],"discriminative":[135],"representations.":[137],"discriminates":[140],"instance":[141],"same":[147],"video,":[148],"whereas":[149],"aims":[153],"discriminate":[155],"consistent":[156],"from":[158],"different":[159],"videos":[160],"order":[162],"distinctive":[166],"Extensive":[169],"experiments":[170],"on":[171],"kinds":[172],"architectures":[174],"datasets":[176],"i.e,":[177],"PoseTrack2017,":[178],"PoseTrack2018":[179],"PoseTrack2021":[181],"show":[182],"HICCON":[184],"achieves":[185],"about":[186],"1.5%":[187],"improvement":[188],"than":[189],"baseline.":[190],"Besides,":[191],"proposed":[193],"method":[194],"unleashes":[195],"potential":[197],"contrastive":[200],"learning":[201],"field.":[204]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}