{"id":"https://openalex.org/W4408345745","doi":"https://doi.org/10.1109/icassp49660.2025.10888834","title":"KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration","display_name":"KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345745","doi":"https://doi.org/10.1109/icassp49660.2025.10888834"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101417093","display_name":"Chengyuan Li","orcid":"https://orcid.org/0000-0002-4422-6584"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyuan Li","raw_affiliation_strings":["Southeast University,College of Software Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,College of Software Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021372366","display_name":"Suyang Zhou","orcid":"https://orcid.org/0000-0002-0802-9858"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Suyang Zhou","raw_affiliation_strings":["Southeast University,College of Software Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,College of Software Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067437467","display_name":"Jieping Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieping Kong","raw_affiliation_strings":["Southeast University,College of Software Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,College of Software Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057689304","display_name":"Lei Qi","orcid":"https://orcid.org/0000-0003-3300-5345"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Qi","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057436798","display_name":"Hui Xue","orcid":"https://orcid.org/0000-0002-5856-4445"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xue","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T13018","display_name":"Seismology and Earthquake Studies","score":0.9657999873161316,"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":0.9401999711990356,"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/modal","display_name":"Modal","score":0.6946727633476257},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6471266746520996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5749626159667969},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5424782037734985},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.44790196418762207},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.44213518500328064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3761942386627197},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.17341694235801697},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.13771885633468628}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6946727633476257},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6471266746520996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5749626159667969},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5424782037734985},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.44790196418762207},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.44213518500328064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3761942386627197},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.17341694235801697},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.13771885633468628},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2910094941","https://openalex.org/W2923486253","https://openalex.org/W2944774584","https://openalex.org/W2948982773","https://openalex.org/W2963351448","https://openalex.org/W3034328552","https://openalex.org/W3135057764","https://openalex.org/W3169077988","https://openalex.org/W3169651898","https://openalex.org/W3198377975","https://openalex.org/W3209793239","https://openalex.org/W4200434100","https://openalex.org/W4312605624","https://openalex.org/W4312960790","https://openalex.org/W4385988806","https://openalex.org/W4386065385","https://openalex.org/W4386065763","https://openalex.org/W4402703054","https://openalex.org/W6765069029","https://openalex.org/W6767471572","https://openalex.org/W6791353385","https://openalex.org/W6851740254","https://openalex.org/W6858057904","https://openalex.org/W6860217881","https://openalex.org/W6863786681"],"related_works":["https://openalex.org/W2806741695","https://openalex.org/W4290647774","https://openalex.org/W3189286258","https://openalex.org/W3207797160","https://openalex.org/W3210364259","https://openalex.org/W4300558037","https://openalex.org/W2667207928","https://openalex.org/W2912112202","https://openalex.org/W4377864969","https://openalex.org/W3120251014"],"abstract_inverted_index":{"Zero-shot":[0],"anomaly":[1,42,56,117,168],"detection":[2],"(ZSAD)":[3],"identifies":[4],"anomalies":[5],"without":[6],"needing":[7],"training":[8],"samples":[9],"from":[10,85,95],"the":[11,120,131],"target":[12],"dataset,":[13],"essential":[14],"for":[15,122,141],"scenarios":[16],"with":[17,54,135,163],"privacy":[18],"concerns":[19],"or":[20,41],"limited":[21],"data.":[22],"Vision-language":[23],"models":[24],"like":[25],"CLIP":[26,52,132],"show":[27],"potential":[28],"in":[29,174],"ZSAD":[30,75,175],"but":[31],"have":[32],"limitations:":[33],"relying":[34],"on":[35,60],"manually":[36],"crafted":[37],"fixed":[38,123],"textual":[39,164],"descriptions":[40],"prompts":[43,125],"is":[44],"time-consuming":[45],"and":[46,51,91,126,146,158,179],"prone":[47],"to":[48,114,186],"semantic":[49],"ambiguity,":[50],"struggles":[53],"pixel-level":[55,167],"segmentation,":[57],"focusing":[58],"more":[59],"global":[61,160],"semantics":[62],"than":[63],"local":[64,151,155],"details.":[65],"To":[66],"address":[67],"these":[68],"limitations,":[69],"We":[70],"introduce":[71],"KAnoCLIP,":[72],"a":[73,86,96,109],"novel":[74],"framework":[76],"that":[77],"leverages":[78],"vision-language":[79],"models.":[80],"KAnoCLIP":[81,129,170],"combines":[82],"general":[83],"knowledge":[84,94],"Large":[87],"Language":[88],"Model":[89],"(GPT-3.5)":[90],"fine-grained,":[92],"image-specific":[93],"Visual":[97],"Question":[98],"Answering":[99],"system":[100],"(Llama3)":[101],"via":[102],"Knowledge-Driven":[103],"Prompt":[104],"Learning":[105],"(KnPL).":[106],"KnPL":[107],"uses":[108],"knowledge-driven":[110],"(KD)":[111],"loss":[112],"function":[113],"create":[115],"learnable":[116],"prompts,":[118],"removing":[119],"need":[121],"text":[124],"enhancing":[127,166],"generalization.":[128],"includes":[130],"visual":[133,152,161],"encoder":[134],"V-V":[136],"attention":[137],"(CLIP-VV),":[138],"Bi-Directional":[139],"Cross-Attention":[140],"Multi-Level":[142],"Cross-Modal":[143],"Interaction":[144],"(Bi-CMCI),":[145],"Conv-Adapter.":[147],"These":[148],"components":[149],"preserve":[150],"semantics,":[153],"improve":[154],"cross-modal":[156],"fusion,":[157],"align":[159],"features":[162],"information,":[165],"detection.":[169],"achieves":[171],"state-of-the-art":[172],"performance":[173],"across":[176],"12":[177],"industrial":[178],"medical":[180],"datasets,":[181],"demonstrating":[182],"superior":[183],"generalization":[184],"compared":[185],"existing":[187],"methods.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}