{"id":"https://openalex.org/W4406859202","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848778","title":"Automatic Prompt Generation and Grounding Object Detection for Zero-Shot Image Anomaly Detection","display_name":"Automatic Prompt Generation and Grounding Object Detection for Zero-Shot Image Anomaly Detection","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406859202","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848778"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5004935515","display_name":"Tsun-Hin Cheung","orcid":"https://orcid.org/0000-0001-5467-6872"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsun-Hin Cheung","raw_affiliation_strings":["New Territories,Centre for Advances in Reliability and Safety,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Territories,Centre for Advances in Reliability and Safety,Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ka-Chun Fung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ka-Chun Fung","raw_affiliation_strings":["New Territories,Centre for Advances in Reliability and Safety,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Territories,Centre for Advances in Reliability and Safety,Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Songjiang Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songjiang Lai","raw_affiliation_strings":["New Territories,Centre for Advances in Reliability and Safety,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Territories,Centre for Advances in Reliability and Safety,Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087429791","display_name":"Kwan-Ho Lin","orcid":"https://orcid.org/0000-0002-2216-9590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kwan-Ho Lin","raw_affiliation_strings":["New Territories,Centre for Advances in Reliability and Safety,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Territories,Centre for Advances in Reliability and Safety,Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004305684","display_name":"Vincent Ng","orcid":"https://orcid.org/0000-0002-5114-3883"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Ng","raw_affiliation_strings":["New Territories,Centre for Advances in Reliability and Safety,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Territories,Centre for Advances in Reliability and Safety,Hong Kong","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019678322","display_name":"Kin\u2010Man Lam","orcid":"https://orcid.org/0000-0002-0422-8454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kin-Man Lam","raw_affiliation_strings":["New Territories,Centre for Advances in Reliability and Safety,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Territories,Centre for Advances in Reliability and Safety,Hong Kong","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68633738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9980000257492065,"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":0.9980000257492065,"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":0.986299991607666,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9750999808311462,"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/anomaly-detection","display_name":"Anomaly detection","score":0.6749356985092163},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6294812560081482},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5885393023490906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5655298233032227},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5558133721351624},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5350236892700195},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4490266740322113},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42561084032058716},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.42415156960487366},{"id":"https://openalex.org/keywords/ground-zero","display_name":"Ground zero","score":0.42077505588531494},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.4142736792564392},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35767072439193726},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1729961335659027}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6749356985092163},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6294812560081482},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5885393023490906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5655298233032227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5558133721351624},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5350236892700195},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4490266740322113},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42561084032058716},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.42415156960487366},{"id":"https://openalex.org/C2780518707","wikidata":"https://www.wikidata.org/wiki/Q685332","display_name":"Ground zero","level":2,"score":0.42077505588531494},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.4142736792564392},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35767072439193726},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1729961335659027},{"id":"https://openalex.org/C185544564","wikidata":"https://www.wikidata.org/wiki/Q81197","display_name":"Nuclear physics","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2251512949","https://openalex.org/W2948982773","https://openalex.org/W2963037989","https://openalex.org/W2986803748","https://openalex.org/W3147184966","https://openalex.org/W3152635971","https://openalex.org/W3167979994","https://openalex.org/W3169651898","https://openalex.org/W4288758332","https://openalex.org/W4312605624","https://openalex.org/W4319597842","https://openalex.org/W4386065385","https://openalex.org/W4386566508","https://openalex.org/W4387272106","https://openalex.org/W4390873163","https://openalex.org/W4404612908","https://openalex.org/W6774611950","https://openalex.org/W6777869702","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6850625674","https://openalex.org/W6851513886","https://openalex.org/W6851592950","https://openalex.org/W6869489350"],"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":{"Identifying":[0],"defects":[1,140],"and":[2,20,68,124,141,155],"anomalies":[3,142],"in":[4,86,135,159],"industrial":[5,34,119,160],"products":[6],"is":[7],"a":[8,27,39,53,74,102],"critical":[9],"quality":[10,157],"control":[11,158],"task.":[12],"Traditional":[13],"manual":[14],"inspection":[15],"methods":[16],"are":[17],"slow,":[18],"subjective,":[19],"error-prone.":[21],"In":[22],"this":[23,130],"work,":[24],"we":[25,90],"propose":[26],"novel":[28],"zero-shot":[29,103],"training-free":[30],"approach":[31],"for":[32,146],"automated":[33],"image":[35,95],"anomaly":[36],"detection":[37,77],"using":[38,101],"multi-modal":[40],"machine":[41],"learning":[42],"pipeline,":[43],"consisting":[44],"of":[45,66,118,129,139],"three":[46],"foundation":[47],"models.":[48],"Our":[49,113,149],"method":[50],"first":[51],"uses":[52],"large":[54],"language":[55],"model,":[56,78,106],"i.e.,":[57],"GPT-3.":[58],"generate":[59],"text":[60],"prompts":[61,100],"describing":[62],"the":[63,84,87,92,98,127,144],"expected":[64],"appearances":[65],"normal":[67],"abnormal":[69],"products.":[70],"We":[71],"then":[72],"use":[73],"grounding":[75],"object":[76],"called":[79,107],"Grounding":[80],"DINO,":[81],"to":[82,97,109],"locate":[83],"product":[85,94,120],"image.":[88],"Finally,":[89],"compare":[91],"cropped":[93],"patches":[96],"generated":[99],"image-text":[104],"matching":[105],"CLIP,":[108],"identify":[110],"any":[111],"anomalies.":[112],"experiments":[114],"on":[115],"two":[116],"datasets":[117],"images,":[121],"namely":[122],"MVTec-AD":[123],"VisA,":[125],"demonstrate":[126],"effectiveness":[128],"method,":[131],"achieving":[132],"high":[133],"accuracy":[134],"detecting":[136],"various":[137],"types":[138],"without":[143],"need":[145],"model":[147,151],"training.":[148],"proposed":[150],"enables":[152],"efficient,":[153],"scalable,":[154],"objective":[156],"manufacturing":[161],"settings.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}