{"id":"https://openalex.org/W7125435559","doi":"https://doi.org/10.1109/tcyb.2026.3651630","title":"VTFusion: A Vision\u2013Text Multimodal Fusion Network for Few-Shot Anomaly Detection","display_name":"VTFusion: A Vision\u2013Text Multimodal Fusion Network for Few-Shot Anomaly Detection","publication_year":2026,"publication_date":"2026-01-21","ids":{"openalex":"https://openalex.org/W7125435559","doi":"https://doi.org/10.1109/tcyb.2026.3651630","pmid":"https://pubmed.ncbi.nlm.nih.gov/41564061"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2026.3651630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2026.3651630","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5123541116","display_name":"Yuxin Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Jiang","raw_affiliation_strings":["National Center of Technology Innovation for Intelligent Design and Numerical Control, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0005-2419-0149","affiliations":[{"raw_affiliation_string":"National Center of Technology Innovation for Intelligent Design and Numerical Control, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123596322","display_name":"Yunkang Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yunkang Cao","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-7619-6618","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104326368","display_name":"Yuqi Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Cheng","raw_affiliation_strings":["National Center of Technology Innovation for Intelligent Design and Numerical Control, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-1994-7301","affiliations":[{"raw_affiliation_string":"National Center of Technology Innovation for Intelligent Design and Numerical Control, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123560593","display_name":"Yiheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiheng Zhang","raw_affiliation_strings":["National Center of Technology Innovation for Intelligent Design and Numerical Control, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0000-5620-0499","affiliations":[{"raw_affiliation_string":"National Center of Technology Innovation for Intelligent Design and Numerical Control, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123593464","display_name":"Weiming Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Shen","raw_affiliation_strings":["National Center of Technology Innovation for Intelligent Design and Numerical Control, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-5204-7992","affiliations":[{"raw_affiliation_string":"National Center of Technology Innovation for Intelligent Design and Numerical Control, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.1051,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96200976,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"56","issue":"6","first_page":"3406","last_page":"3415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8537999987602234,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8537999987602234,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03269999846816063,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.012600000016391277,"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/robustness","display_name":"Robustness (evolution)","score":0.59579998254776},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5720999836921692},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5087000131607056},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4553999900817871},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.412200003862381},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.39730000495910645},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.373199999332428},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3424000144004822},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33809998631477356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329000234603882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.628000020980835},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.59579998254776},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5720999836921692},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3077000081539154},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C526921623","wikidata":"https://www.wikidata.org/wiki/Q190117","display_name":"Automotive industry","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.25540000200271606},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2026.3651630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2026.3651630","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:41564061","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41564061","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6372687220573425}],"awards":[{"id":"https://openalex.org/G2774465445","display_name":null,"funder_award_id":"HUST:2021GCRC058","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320324873","display_name":"South University of Science and Technology of China","ror":"https://ror.org/049tv2d57"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Few-shot":[0],"anomaly":[1,163],"detection":[2],"(FSAD)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,82,137,146,156,206],"critical":[8],"paradigm":[9],"for":[10,44,88,101],"identifying":[11],"irregularities":[12],"using":[13],"scarce":[14],"normal":[15],"references.":[16],"While":[17],"recent":[18],"methods":[19],"have":[20],"integrated":[21],"textual":[22,66],"semantics":[23,42],"to":[24,53,57,109,132],"complement":[25],"visual":[26,64],"data,":[27],"they":[28],"predominantly":[29],"rely":[30],"on":[31,34,93,190,205],"features":[32],"pretrained":[33,118],"natural":[35],"scenes,":[36],"thereby":[37],"neglecting":[38],"the":[39,59,114,177,187,191],"granular,":[40],"domain-specific":[41],"essential":[43],"industrial":[45,121,210,225],"inspection.":[46],"Furthermore,":[47,198],"prevalent":[48],"fusion":[49,85,141,147],"strategies":[50],"often":[51],"resort":[52],"superficial":[54],"concatenation,":[55],"failing":[56],"address":[58],"inherent":[60],"semantic":[61],"misalignment":[62],"between":[63,117],"and":[65,104,120,155,184,194],"modalities,":[67],"which":[68],"compromises":[69],"robustness":[70],"against":[71],"cross-modal":[72,152],"interference.":[73],"To":[74],"bridge":[75],"these":[76],"gaps,":[77],"this":[78,123,216],"study":[79],"proposes":[80],"VTFusion,":[81],"vision-text":[83],"multimodal":[84,139,166],"framework":[86,91],"tailored":[87],"FSAD.":[89],"The":[90],"rests":[92],"two":[94],"core":[95],"designs.":[96],"First,":[97],"adaptive":[98],"feature":[99,134],"extractors":[100],"both":[102],"image":[103],"text":[105],"modalities":[106],"are":[107],"introduced":[108,214],"learn":[110],"task-specific":[111],"representations,":[112],"bridging":[113],"domain":[115],"gap":[116],"models":[119],"data;":[122],"is":[124,143],"further":[125,218],"augmented":[126],"by":[127],"generating":[128],"diverse":[129],"synthetic":[130],"anomalies":[131],"enhance":[133],"discriminability.":[135],"Second,":[136],"dedicated":[138],"prediction":[140],"module":[142],"developed,":[144],"comprising":[145],"block":[148],"that":[149,159],"facilitates":[150],"rich":[151],"information":[153],"exchange":[154],"segmentation":[157],"network":[158],"generates":[160],"refined":[161],"pixel-level":[162],"maps":[164],"under":[165,176],"guidance.":[167],"VTFusion":[168,199],"significantly":[169],"advances":[170],"FSAD":[171],"performance,":[172],"achieving":[173],"image-level":[174],"area":[175],"receiver":[178],"operating":[179],"characteristics":[180],"(AUROCs)":[181],"of":[182,203,209],"96.8%":[183],"86.2%":[185],"in":[186,215,223],"2-shot":[188],"scenario":[189],"MVTec":[192],"AD":[193],"VisA":[195],"datasets,":[196],"respectively.":[197],"achieves":[200],"an":[201],"AUPRO":[202],"93.5%":[204],"real-world":[207],"dataset":[208],"automotive":[211],"plastic":[212],"parts":[213],"article,":[217],"demonstrating":[219],"its":[220],"practical":[221],"applicability":[222],"demanding":[224],"scenarios.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-23T00:00:00"}