{"id":"https://openalex.org/W7118505886","doi":"https://doi.org/10.1109/tmm.2026.3651129","title":"Transferring and Refining Visual-Semantic Priors via Graph-Enhanced CLIP for 3D Hand Pose Estimation","display_name":"Transferring and Refining Visual-Semantic Priors via Graph-Enhanced CLIP for 3D Hand Pose Estimation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7118505886","doi":"https://doi.org/10.1109/tmm.2026.3651129"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651129","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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":null,"display_name":"Tingting Liu","orcid":"https://orcid.org/0000-0002-0555-7671"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Liu","raw_affiliation_strings":["School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-0555-7671","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004714275","display_name":"Ji Gan","orcid":"https://orcid.org/0000-0001-6041-588X"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Gan","raw_affiliation_strings":["School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0001-6041-588X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061201566","display_name":"Jiaxu Leng","orcid":"https://orcid.org/0000-0003-2802-8139"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxu Leng","raw_affiliation_strings":["School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0003-2802-8139","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuang Li","orcid":"https://orcid.org/0000-0003-4258-3163"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Li","raw_affiliation_strings":["School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0003-4258-3163","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065811458","display_name":"Lei Cheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":["School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0003-5553-2768","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120988538","display_name":"Xinbo Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbo Gao","raw_affiliation_strings":["School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-7985-0037","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03780811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"3147","last_page":"3159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.8206999897956848,"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":0.8206999897956848,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.09740000218153,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.013799999840557575,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.7763000130653381},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.7595999836921692},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6269999742507935},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5058000087738037},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4936999976634979},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47690001130104065},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.4519999921321869},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43860000371932983},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4097000062465668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478999733924866},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7763000130653381},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7595999836921692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7293999791145325},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6269999742507935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5777000188827515},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5058000087738037},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.4519999921321869},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.2590000033378601},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651129","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","score":0.4306336045265198,"id":"https://metadata.un.org/sdg/1"}],"awards":[{"id":"https://openalex.org/G3453920714","display_name":null,"funder_award_id":"62221005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3913156051","display_name":null,"funder_award_id":"62472060","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4297946667","display_name":null,"funder_award_id":"U22A2096","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4981513040","display_name":null,"funder_award_id":"62206035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G742640457","display_name":null,"funder_award_id":"2025MD774186","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,18,82,209],"hand":[1,19,83,96,157,166,186,210],"pose":[2,20,84,187,211],"estimation":[3,21,97],"is":[4,109,126,216],"crucial":[5],"for":[6,17,50,80,134,181,208],"many":[7],"human-computer":[8],"interaction":[9],"applications.":[10],"However,":[11],"existing":[12],"deep":[13],"neural":[14],"networks":[15],"(DNNs)":[16],"suffer":[22],"from":[23,117],"poor":[24],"generalizability":[25],"due":[26],"to":[27,69,73,93,111,144,174],"data":[28],"scarcity":[29],"and":[30,75,105,128,159],"a":[31,66,90],"lack":[32],"of":[33,57,156,165],"domain-specific":[34,78,147],"knowledge.":[35,60],"In":[36],"contrast,":[37],"humans":[38],"remain":[39],"far":[40],"better":[41,81,190],"than":[42],"DNNs":[43],"at":[44,218],"learning;":[45],"Humans":[46],"require":[47],"fewer":[48],"samples":[49],"learning":[51,100,108],"new":[52],"concepts":[53],"under":[54],"the":[55,95,101,118,146,152,161,177,182],"guidance":[56],"their":[58],"prior":[59],"Inspired":[61],"by":[62,149],"this,":[63],"we":[64,87,139],"propose":[65],"graph-enhanced":[67,197],"CLIP":[68,92,179,198],"deliver":[70],"visual-semantic":[71,115],"priors":[72,116],"DNNs,":[74],"provide":[76],"refined":[77],"knowledge":[79,148],"estimation.":[85,212],"Specifically,":[86],"first":[88],"introduce":[89,140],"pre-trained":[91,119],"guide":[94],"model":[98],"in":[99],"semantic-aware":[102],"visual":[103,136],"features,":[104],"text-free":[106],"contrastive":[107],"proposed":[110,196],"effectively":[112],"transfer":[113],"high-level":[114],"large":[120],"multimodal":[121],"models.":[122],"Notably,":[123],"our":[124,195],"strategy":[125],"data-agnostic":[127],"avoids":[129],"designing":[130],"hand-crafted":[131],"text":[132],"prompts":[133],"various":[135],"inputs.":[137],"Second,":[138],"novel":[141],"graph":[142,170],"Transformers":[143,171],"refine":[145,176],"fully":[150],"exploiting":[151],"local":[153],"adjacent":[154],"relations":[155],"joints":[158],"capturing":[160],"global":[162],"structure":[163],"representations":[164],"poses.":[167],"The":[168,213],"introduced":[169],"are":[172],"supposed":[173],"further":[175],"generalized":[178],"feature":[180],"downstream":[183],"task":[184],"(i.e.,":[185],"estimation)":[188],"with":[189],"performance.":[191],"Experiments":[192],"show":[193],"that":[194],"achieves":[199],"state-of-the-art":[200],"performances":[201],"on":[202],"benchmark":[203],"datasets,":[204],"demonstrating":[205],"its":[206],"effectiveness":[207],"source":[214],"code":[215],"available":[217],"<uri":[219],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[220],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/TLiu2832/TRVSP-GE-CLIP</uri>.":[221]},"counts_by_year":[],"updated_date":"2026-04-25T06:01:18.069262","created_date":"2026-01-08T00:00:00"}