{"id":"https://openalex.org/W4414360097","doi":"https://doi.org/10.24963/ijcai.2025/80","title":"Towards VLM-based Hybrid Explainable Prompt Enhancement for Zero-Shot Industrial Anomaly Detection","display_name":"Towards VLM-based Hybrid Explainable Prompt Enhancement for Zero-Shot Industrial Anomaly Detection","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360097","doi":"https://doi.org/10.24963/ijcai.2025/80"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/80","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/80","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-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/A5103079093","display_name":"Weichao Cai","orcid":"https://orcid.org/0009-0002-6060-655X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weichao Cai","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058012950","display_name":"Weiliang Huang","orcid":"https://orcid.org/0000-0001-7273-7325"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Weiliang Huang","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044965902","display_name":"Yunkang Cao","orcid":"https://orcid.org/0000-0001-7619-6618"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunkang Cao","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101441843","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0003-1490-2171"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006290691","display_name":"Fei Yuan","orcid":"https://orcid.org/0000-0003-0171-6505"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yuan","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048088901","display_name":"Bob Zhang","orcid":"https://orcid.org/0000-0003-2497-9519"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Bob Zhang","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017617923","display_name":"Jie Wen","orcid":"https://orcid.org/0000-0001-9554-2379"},"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":"Jie Wen","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103079093"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12215852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"711","last_page":"719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9980999827384949,"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":0.9980999827384949,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9090999960899353,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7864000201225281},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6689000129699707},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5461000204086304},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.46219998598098755},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.3278999924659729},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.32420000433921814}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7864000201225281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7202000021934509},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6689000129699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6051999926567078},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2779119184","wikidata":"https://www.wikidata.org/wiki/Q294350","display_name":"ALARM","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2736000120639801}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/80","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/80","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-Shot":[0],"Industrial":[1],"Anomaly":[2],"Detection":[3],"(ZSIAD)":[4],"aims":[5],"to":[6,18,50,54,75,110,127,145],"identify":[7],"and":[8,38,77,118,133,159],"localize":[9],"anomalies":[10,84,155],"in":[11,30],"industrial":[12,43,83,166],"images":[13],"from":[14],"unseen":[15],"categories.":[16],"Owing":[17],"the":[19,34,40,55,79,88,94,104,112,128,140,173,188],"powerful":[20],"generalization":[21],"capabilities,":[22],"Vision-Language":[23],"Models":[24],"(VLMs)":[25],"have":[26,48,170],"achieved":[27],"growing":[28],"interest":[29],"ZSIAD.":[31,100],"To":[32,86],"guide":[33],"model":[35,56,129,189],"toward":[36],"understanding":[37],"localizing":[39],"semantically":[41],"complex":[42],"anomalies,":[44,71],"existing":[45],"VLM-based":[46],"methods":[47,65],"attempted":[49],"provide":[51,123,187],"additional":[52],"prompts":[53,126,149,186],"through":[57,130],"learnable":[58],"text":[59,125],"prompt":[60,96],"templates.":[61],"However,":[62],"these":[63],"zero-shot":[64],"lack":[66],"detailed":[67,113,124],"descriptions":[68],"of":[69,82,154],"specific":[70],"making":[72],"it":[73],"difficult":[74],"classify":[76],"segment":[78],"diverse":[80],"range":[81],"accurately.":[85],"address":[87],"aforementioned":[89],"issue,":[90],"we":[91,102,138],"firstly":[92],"propose":[93],"multi-stage":[95],"generation":[97],"agent":[98],"for":[99,150,195],"Specifically,":[101],"leverage":[103],"Multi-modal":[105],"Language":[106],"Large":[107],"Model":[108,143],"(MLLM)":[109],"articulate":[111],"differential":[114],"information":[115],"between":[116],"normal":[117],"test":[119],"samples,":[120],"which":[121],"can":[122],"further":[131],"refinement":[132],"anti-false":[134],"alarm":[135],"constraint.":[136],"Moreover,":[137],"introduce":[139],"Visual":[141],"Fundamental":[142],"(VFM)":[144],"generate":[146],"anomaly-related":[147],"attention":[148],"more":[151,192],"accurate":[152],"localization":[153],"with":[156,190],"varying":[157],"sizes":[158],"shapes.":[160],"Extensive":[161],"experiments":[162],"on":[163],"seven":[164],"real-world":[165],"anomaly":[167,196],"detection":[168],"datasets":[169],"shown":[171],"that":[172],"proposed":[174],"method":[175],"not":[176],"only":[177],"outperforms":[178],"recent":[179],"SOTA":[180],"methods,":[181],"but":[182],"also":[183],"its":[184],"explainable":[185],"a":[191],"intuitive":[193],"basis":[194],"identification.":[197]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}