{"id":"https://openalex.org/W4409473720","doi":"https://doi.org/10.1109/tits.2025.3532731","title":"Improving Surface Defect Detection for Trains Based on Visual-Language Knowledge Guidance on Tiny Datasets","display_name":"Improving Surface Defect Detection for Trains Based on Visual-Language Knowledge Guidance on Tiny Datasets","publication_year":2025,"publication_date":"2025-04-15","ids":{"openalex":"https://openalex.org/W4409473720","doi":"https://doi.org/10.1109/tits.2025.3532731"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2025.3532731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3532731","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","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/A5108190869","display_name":"Kaiyu Lei","orcid":"https://orcid.org/0009-0005-4964-3570"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaiyan Lei","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-4964-3570","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013051763","display_name":"Zhiquan Qi","orcid":"https://orcid.org/0000-0001-9289-9110"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiquan Qi","raw_affiliation_strings":["Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9289-9110","affiliations":[{"raw_affiliation_string":"Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087001696","display_name":"Song Jin","orcid":"https://orcid.org/0000-0003-2228-887X"},"institutions":[{"id":"https://openalex.org/I4210106004","display_name":"Guangzhou Railway Polytechnic","ror":"https://ror.org/01qjhbg05","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210106004"]},{"id":"https://openalex.org/I4210113138","display_name":"Guangzhou Automobile Group (China)","ror":"https://ror.org/026fzn952","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210113138"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Song","raw_affiliation_strings":["China Railway Guangzhou Group Company Ltd., Guangzhou, China","China Railway Guangzhou Group Company Ltd, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Railway Guangzhou Group Company Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I4210106004","https://openalex.org/I4210113138"]},{"raw_affiliation_string":"China Railway Guangzhou Group Company Ltd, Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108190869"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.1126,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77841746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"26","issue":"6","first_page":"9080","last_page":"9093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.9318000078201294,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural 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/train","display_name":"Train","score":0.6368887424468994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5082039833068848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41651687026023865},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3864099979400635},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34117406606674194},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1187613308429718},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.09471490979194641}],"concepts":[{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.6368887424468994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5082039833068848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41651687026023865},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3864099979400635},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34117406606674194},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1187613308429718},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.09471490979194641}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2025.3532731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3532731","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6214398767","display_name":null,"funder_award_id":"T2293774","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6463167065","display_name":null,"funder_award_id":"72231010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"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":43,"referenced_works":["https://openalex.org/W2570343428","https://openalex.org/W2789305678","https://openalex.org/W2948982773","https://openalex.org/W2963037989","https://openalex.org/W2990559999","https://openalex.org/W3011799887","https://openalex.org/W3018757597","https://openalex.org/W3098102277","https://openalex.org/W3128247733","https://openalex.org/W3143042575","https://openalex.org/W3196806685","https://openalex.org/W4206049640","https://openalex.org/W4221140369","https://openalex.org/W4297676427","https://openalex.org/W4312734855","https://openalex.org/W4319779677","https://openalex.org/W4375861378","https://openalex.org/W4382203375","https://openalex.org/W4385245566","https://openalex.org/W4386065385","https://openalex.org/W4386075561","https://openalex.org/W4386076325","https://openalex.org/W4386076397","https://openalex.org/W4390872587","https://openalex.org/W4392172801","https://openalex.org/W4392397308","https://openalex.org/W4393241421","https://openalex.org/W4394951205","https://openalex.org/W4402703054","https://openalex.org/W4402716047","https://openalex.org/W4402754006","https://openalex.org/W4403770406","https://openalex.org/W4404853040","https://openalex.org/W6750227808","https://openalex.org/W6791353385","https://openalex.org/W6798838024","https://openalex.org/W6802517928","https://openalex.org/W6856831935","https://openalex.org/W6857911570","https://openalex.org/W6858057904","https://openalex.org/W6858587289","https://openalex.org/W6861728866","https://openalex.org/W6866707656"],"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":{"Efficient":[0],"and":[1,20,65,83,106,126,136,215,225,241,243,251],"accurate":[2],"detection":[3,26,40],"of":[4,52,89,103,163,195,238],"surface":[5,38,212],"defects":[6,135,230],"on":[7,120,209,228],"trains":[8],"is":[9],"crucial":[10],"for":[11,57,96],"ensuring":[12],"train":[13,37,211],"safety.":[14],"However,":[15],"the":[16,54,58,67,85,121,161,187,192],"insufficient":[17,59],"defect":[18,25,39,60,117,149,152,213,218],"samples":[19],"their":[21],"diverse":[22,107],"patterns":[23],"make":[24],"in":[27,62],"complex":[28,104],"environments":[29],"highly":[30],"challenging.":[31],"This":[32,99,130],"paper":[33],"proposes":[34],"a":[35,245],"novel":[36],"model":[41,55],"(ViLG)":[42],"via":[43],"visual-language":[44],"knowledge":[45,51],"guidance.":[46],"By":[47],"leveraging":[48],"broad":[49],"semantic":[50,101,122],"CLIP,":[53,80],"compensates":[56],"semantics":[61,162],"tiny":[63],"datasets":[64,214],"enhances":[66,84],"ability":[68,95],"to":[69,133],"recognize":[70],"unseen":[71,229],"defects.":[72,108,164],"First,":[73],"we":[74,110,141,172],"propose":[75,111,142,173],"Visual":[76],"Feature":[77],"Guidance":[78],"with":[79,151,168,205,231,235],"which":[81,115,146,175],"enriches":[82],"global":[86,127,188],"representation":[87],"capabilities":[88],"backbone":[90],"while":[91],"preserving":[92],"its":[93],"self-learning":[94],"visual":[97,196],"representations.":[98],"improves":[100],"understanding":[102],"scenarios":[105,167],"Second,":[109],"Defect":[112],"Query":[113],"Selector,":[114],"selects":[116],"queries":[118,150],"based":[119],"relevance":[123],"between":[124],"texts":[125],"feature":[128,181],"embeddings.":[129],"increases":[131],"attention":[132],"potential":[134],"reduces":[137],"missed":[138],"detections.":[139],"Finally,":[140],"Semantic":[143],"Consistency":[144],"Loss,":[145],"semantically":[147],"aligns":[148],"prompts.":[153],"With":[154],"additional":[155],"cross-modal":[156],"supervision":[157],"signals,":[158],"it":[159],"refines":[160],"For":[165],"real-world":[166],"normal":[169],"reference":[170],"images,":[171],"ViLG+,":[174],"effectively":[176,190],"filters":[177],"false":[178,248,252],"positives":[179],"using":[180],"similarity.":[182],"It":[183],"further":[184],"verifies":[185],"that":[186],"embeddings":[189],"represent":[191],"overall":[193],"structure":[194],"scenes":[197],"as":[198,200],"well":[199],"subtle":[201],"local":[202],"features.":[203],"Compared":[204],"other":[206],"advanced":[207],"methods":[208],"two":[210,216],"public":[217],"datasets,":[219],"ViLG":[220],"shows":[221],"higher":[222],"precision,":[223],"recall,":[224],"average":[226,236],"precision":[227],"relatively":[232],"faster":[233],"speed,":[234],"improvements":[237],"23.58,":[239],"3.23,":[240],"6.05,":[242],"has":[244],"more":[246],"balanced":[247],"positive":[249],"rate":[250],"negative":[253],"rate.":[254]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}