{"id":"https://openalex.org/W4403791158","doi":"https://doi.org/10.1145/3664647.3681190","title":"Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection","display_name":"Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791158","doi":"https://doi.org/10.1145/3664647.3681190"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5043314002","display_name":"Jiaqi Zhu","orcid":"https://orcid.org/0000-0002-9442-0318"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaqi Zhu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001683040","display_name":"Shaofeng Cai","orcid":"https://orcid.org/0000-0001-8605-076X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shaofeng Cai","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050766","display_name":"Fang Deng","orcid":"https://orcid.org/0000-0002-1111-7285"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Deng","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024892041","display_name":"Beng Chin Ooi","orcid":"https://orcid.org/0000-0003-4446-1100"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Beng Chin Ooi","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049217904","display_name":"Junran Wu","orcid":"https://orcid.org/0000-0001-6742-4332"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junran Wu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043314002"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":6.6028,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.97221893,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7380539178848267},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5939334034919739},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5501096248626709},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5398338437080383},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.37371575832366943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2990402281284332},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.24566048383712769},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0941312313079834},{"id":"https://openalex.org/keywords/condensed-matter-physics","display_name":"Condensed matter physics","score":0.061506837606430054}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7380539178848267},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5939334034919739},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5501096248626709},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5398338437080383},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37371575832366943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2990402281284332},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.24566048383712769},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0941312313079834},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.061506837606430054},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":40,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W2010132303","https://openalex.org/W2062022900","https://openalex.org/W2946273655","https://openalex.org/W2948982773","https://openalex.org/W3035240825","https://openalex.org/W3035802502","https://openalex.org/W3097676403","https://openalex.org/W3117272077","https://openalex.org/W3147184966","https://openalex.org/W3166166117","https://openalex.org/W3169077988","https://openalex.org/W3169651898","https://openalex.org/W3175238080","https://openalex.org/W3176739743","https://openalex.org/W3212044949","https://openalex.org/W4214694907","https://openalex.org/W4230405732","https://openalex.org/W4243930609","https://openalex.org/W4281643792","https://openalex.org/W4285045749","https://openalex.org/W4293518844","https://openalex.org/W4312310776","https://openalex.org/W4312605624","https://openalex.org/W4312772600","https://openalex.org/W4312960937","https://openalex.org/W4319299987","https://openalex.org/W4319300060","https://openalex.org/W4380433160","https://openalex.org/W4380433171","https://openalex.org/W4386065385","https://openalex.org/W4386065608","https://openalex.org/W4386071547","https://openalex.org/W4386075985","https://openalex.org/W4386076332","https://openalex.org/W4387968357","https://openalex.org/W4390874575","https://openalex.org/W4392453402","https://openalex.org/W6838461383","https://openalex.org/W6912494966"],"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/W2972971679"],"abstract_inverted_index":{"Large":[0],"vision-language":[1],"models":[2],"(LVLMs)":[3],"are":[4,54],"markedly":[5],"proficient":[6],"in":[7,175],"deriving":[8],"visual":[9,23],"representations":[10,63],"guided":[11],"by":[12,28,122,152],"natural":[13],"language.":[14],"Recent":[15],"explorations":[16],"have":[17],"utilized":[18],"LVLMs":[19],"to":[20,41,56,87,108,143,159,197],"tackle":[21],"zero-shot":[22,181,199],"anomaly":[24,43,51,75,106,129,150],"detection":[25],"(VAD)":[26],"challenges":[27,90],"pairing":[29],"images":[30],"with":[31],"textual":[32],"descriptions":[33],"indicative":[34],"of":[35,112,187],"normal":[36],"and":[37,59,132,169,192],"abnormal":[38],"conditions,":[39],"referred":[40],"as":[42],"prompts.":[44],"However,":[45],"existing":[46],"approaches":[47],"depend":[48],"on":[49,165,189,194],"static":[50],"prompts":[52,107],"that":[53,70],"prone":[55],"cross-semantic":[57,133],"ambiguity,":[58],"prioritize":[60],"global":[61,158],"image-level":[62],"over":[64],"crucial":[65],"local":[66,145,160],"pixel-level":[67,146],"image-to-text":[68],"alignment":[69,156],"is":[71,120],"necessary":[72],"for":[73,127,148,180],"accurate":[74],"localization.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"present":[81],"ALFA,":[82],"a":[83,92,97,113,123,139],"training-free":[84],"approach":[85],"designed":[86],"address":[88],"these":[89],"via":[91],"unified":[93],"model.":[94],"We":[95,136],"propose":[96],"run-time":[98],"prompt":[99,130],"adaptation":[100,131],"strategy,":[101],"which":[102],"first":[103],"generates":[104],"informative":[105],"leverage":[109],"the":[110,154,166,177],"capabilities":[111],"large":[114],"language":[115,178],"model":[116],"(LLM).":[117],"This":[118],"strategy":[119],"enhanced":[121],"contextual":[124],"scoring":[125],"mechanism":[126],"per-image":[128],"ambiguity":[134],"mitigation.":[135],"further":[137],"introduce":[138],"novel":[140],"fine-grained":[141],"aligner":[142],"fuse":[144],"semantics":[147],"precise":[149],"localization,":[151],"projecting":[153],"image-text":[155],"from":[157],"semantic":[161],"spaces.":[162],"Extensive":[163],"evaluations":[164],"challenging":[167],"MVTec":[168,190],"VisA":[170,195],"datasets":[171],"confirm":[172],"ALFA's":[173],"effectiveness":[174],"harnessing":[176],"potential":[179],"VAD,":[182],"achieving":[183],"significant":[184],"PRO":[185],"improvements":[186],"12.1%":[188],"AD":[191],"8.9%":[193],"compared":[196],"state-of-the-art":[198],"VAD":[200],"approaches.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}