{"id":"https://openalex.org/W7133204151","doi":"https://doi.org/10.1109/tcsvt.2026.3669478","title":"DKGZSL: Leveraging Dynamic Visual-Semantic Knowledge for Generative Zero-Shot Learning","display_name":"DKGZSL: Leveraging Dynamic Visual-Semantic Knowledge for Generative Zero-Shot Learning","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133204151","doi":"https://doi.org/10.1109/tcsvt.2026.3669478"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3669478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3669478","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/A5041289533","display_name":"Jun Hu","orcid":"https://orcid.org/0000-0003-3502-1533"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Hu","raw_affiliation_strings":["School of Computer Science, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-5326-0826","affiliations":[{"raw_affiliation_string":"School of Computer Science, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048763159","display_name":"Min Meng","orcid":"https://orcid.org/0000-0002-5107-5585"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Meng","raw_affiliation_strings":["School of Computer Science, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5107-5585","affiliations":[{"raw_affiliation_string":"School of Computer Science, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121031298","display_name":"Jigang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jigang Liu","raw_affiliation_strings":["Ping An Life Insurance of China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5778-895X","affiliations":[{"raw_affiliation_string":"Ping An Life Insurance of China, Shenzhen, China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127832726","display_name":"Jun Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1922-7283","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jigang Wu","orcid":"https://orcid.org/0000-0002-6470-9794"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jigang Wu","raw_affiliation_strings":["School of Computer Science, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6470-9794","affiliations":[{"raw_affiliation_string":"School of Computer Science, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]}],"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":0.20566973,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"7","first_page":"9349","last_page":"9362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9395999908447266,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9395999908447266,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03629999980330467,"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/T10028","display_name":"Topic Modeling","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/generative-grammar","display_name":"Generative grammar","score":0.5526000261306763},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5202999711036682},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.39719998836517334},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3874000012874603},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3815999925136566},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.3797999918460846},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.3743000030517578},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36000001430511475},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.35269999504089355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8621000051498413},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5526000261306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5508000254631042},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43880000710487366},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3743000030517578},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3522999882698059},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3669478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3669478","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/G1335214334","display_name":null,"funder_award_id":"62172109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4945527307","display_name":null,"funder_award_id":"2025A04J7144","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"Zero-Shot":[1],"Learning":[2],"(GZSL)":[3],"methods":[4],"address":[5],"the":[6,76,136,150,189],"challenge":[7],"of":[8,193],"recognizing":[9],"unseen":[10],"classes":[11],"by":[12],"synthesizing":[13],"visual":[14,104,124],"features,":[15],"thereby":[16],"converting":[17],"ZSL":[18],"into":[19,75,85,102,126],"a":[20,65,86,91,115],"supervised":[21],"learning":[22],"task.":[23],"However,":[24],"existing":[25],"approaches":[26],"are":[27],"predominantly":[28],"constrained":[29],"to":[30,98,149],"two":[31],"multi-stage":[32],"strategies:":[33],"pre-generation":[34],"prior":[35],"knowledge":[36,73,105,140],"enhancement":[37],"and":[38,55,83,129,160,180,191],"post-generation":[39],"feature":[40,77,182],"refinement.":[41],"These":[42],"paradigms":[43],"often":[44],"suffer":[45],"from":[46,142],"error":[47],"propagation":[48],"across":[49],"stages,":[50],"ultimately":[51],"limiting":[52],"generation":[53,82,162],"quality":[54],"representational":[56],"fidelity.":[57],"To":[58,107],"overcome":[59],"these":[60],"limitations,":[61],"we":[62,112],"propose":[63],"DKGZSL,":[64],"novel":[66],"generative":[67],"framework":[68],"that":[69,121,171],"injects":[70],"dynamic":[71,157],"visual-semantic":[72],"directly":[74],"synthesis":[78],"process,":[79],"effectively":[80],"unifying":[81],"refinement":[84],"single":[87],"cohesive":[88],"stage.":[89],"Specifically,":[90],"Knowledge":[92],"Transfer":[93],"Network":[94],"(KTN)":[95],"is":[96,146,199],"introduced":[97],"convert":[99],"semantic":[100,158],"information":[101],"hierarchical":[103,139],"representations.":[106],"ensure":[108],"accurate":[109],"semanticvisual":[110],"alignment,":[111],"further":[113,187],"design":[114],"Semantic-Oriented":[116],"Visual":[117],"Refinement":[118],"(SOVR)":[119],"module":[120],"reshapes":[122],"real":[123],"features":[125],"semantically":[127],"aligned":[128],"noise-suppressed":[130],"representations,":[131],"providing":[132],"precise":[133],"guidance":[134,159],"for":[135],"KTN.":[137],"Moreover,":[138],"extracted":[141],"each":[143,194],"KTN":[144],"layer":[145],"progressively":[147],"transmitted":[148],"generator":[151],"via":[152],"Meta-Fusion":[153],"Units":[154],"(MFUs),":[155],"enabling":[156],"improving":[161],"quality.":[163],"Extensive":[164],"experiments":[165],"on":[166],"three":[167],"benchmark":[168],"datasets":[169],"demonstrate":[170],"DKGZSL":[172],"achieves":[173],"consistent":[174],"state-of-the-art":[175],"performance":[176],"with":[177],"both":[178],"ResNet-101":[179],"ViT-B/16":[181],"extractors.":[183],"Comprehensive":[184],"ablation":[185],"studies":[186],"confirm":[188],"effectiveness":[190],"complementarity":[192],"proposed":[195],"component.":[196],"The":[197],"code":[198],"available":[200],"at":[201],"https://github.com/JingHu-gdut/DKGZSL.":[202]},"counts_by_year":[],"updated_date":"2026-07-08T06:17:01.165560","created_date":"2026-03-03T00:00:00"}