{"id":"https://openalex.org/W4403780886","doi":"https://doi.org/10.1145/3664647.3681376","title":"SimCLIP: Refining Image-Text Alignment with Simple Prompts for Zero-/Few-shot Anomaly Detection","display_name":"SimCLIP: Refining Image-Text Alignment with Simple Prompts for Zero-/Few-shot Anomaly Detection","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780886","doi":"https://doi.org/10.1145/3664647.3681376"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681376","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681376","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":"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":null,"display_name":"Chenghao Deng","orcid":"https://orcid.org/0009-0008-2806-6542"},"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":"Chenghao Deng","raw_affiliation_strings":["Institute of Artificial Intelligence, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0008-2806-6542","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103732912","display_name":"Haote Xu","orcid":"https://orcid.org/0000-0001-7106-2207"},"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":"Haote Xu","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0001-7106-2207","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108273273","display_name":"Xiaolu Chen","orcid":"https://orcid.org/0009-0000-2296-4909"},"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":"Xiaolu Chen","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0000-2296-4909","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113389796","display_name":"Huiming Xu","orcid":null},"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":"Haodi Xu","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0001-4915-5738","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068316504","display_name":"Xiaotong Tu","orcid":"https://orcid.org/0000-0002-7190-2429"},"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":"Xiaotong Tu","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-7190-2429","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052820597","display_name":"Xinghao Ding","orcid":"https://orcid.org/0000-0003-2288-5287"},"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":"Xinghao Ding","raw_affiliation_strings":["School of Informatics, Xiamen University & Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0003-2288-5287","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University & Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100772804","display_name":"Yue Huang","orcid":"https://orcid.org/0000-0002-3913-9400"},"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":"Yue Huang","raw_affiliation_strings":["School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-3913-9400","affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1761","last_page":"1770"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.998199999332428,"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":0.998199999332428,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955000281333923,"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/simple","display_name":"Simple (philosophy)","score":0.7209252119064331},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6849460005760193},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5706905126571655},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5585809350013733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5429851412773132},{"id":"https://openalex.org/keywords/refining","display_name":"Refining (metallurgy)","score":0.5182430744171143},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.4918859004974365},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4888851046562195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44791752099990845},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42746812105178833},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34095498919487},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.2018098533153534},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10832095146179199},{"id":"https://openalex.org/keywords/condensed-matter-physics","display_name":"Condensed matter physics","score":0.05978083610534668}],"concepts":[{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.7209252119064331},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6849460005760193},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5706905126571655},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5585809350013733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5429851412773132},{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.5182430744171143},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.4918859004974365},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4888851046562195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44791752099990845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42746812105178833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34095498919487},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2018098533153534},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10832095146179199},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.05978083610534668},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681376","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681376","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2948982773","https://openalex.org/W2963351448","https://openalex.org/W3035524453","https://openalex.org/W3169651898","https://openalex.org/W3177174258","https://openalex.org/W3198377975","https://openalex.org/W4224308101","https://openalex.org/W4226058394","https://openalex.org/W4287113019","https://openalex.org/W4296151208","https://openalex.org/W4312298392","https://openalex.org/W4312310776","https://openalex.org/W4312420092","https://openalex.org/W4312480274","https://openalex.org/W4312605624","https://openalex.org/W4312629998","https://openalex.org/W4312960937","https://openalex.org/W4386065385","https://openalex.org/W4386071547","https://openalex.org/W4386076397","https://openalex.org/W4388543952","https://openalex.org/W4390873118","https://openalex.org/W4390873248","https://openalex.org/W4390873546","https://openalex.org/W4394625837","https://openalex.org/W4402753899","https://openalex.org/W6810081322"],"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":{"Recently,":[0],"large":[1],"pre-trained":[2],"vision-language":[3],"models,":[4],"such":[5],"as":[6],"CLIP,":[7],"have":[8],"demonstrated":[9],"significant":[10],"potential":[11],"in":[12,46,100],"zero-/few-shot":[13],"anomaly":[14,47,95,131],"detection":[15,132],"tasks.":[16,49,133],"However,":[17],"existing":[18],"methods":[19],"not":[20],"only":[21,87],"rely":[22],"on":[23,61,136],"expert":[24],"knowledge":[25],"to":[26,92,128,150],"manually":[27],"craft":[28],"extensive":[29],"text":[30],"prompts":[31],"but":[32],"also":[33],"suffer":[34],"from":[35],"a":[36,55,88],"misalignment":[37,65],"of":[38,70,146],"high-level":[39],"language":[40,127],"features":[41,45],"with":[42],"fine-level":[43],"vision":[44,115,125],"segmentation":[48,98],"In":[50,81],"this":[51,82],"paper,":[52],"we":[53,104],"propose":[54],"method,":[56],"named":[57],"SimCLIP,":[58],"which":[59],"focuses":[60],"refining":[62],"the":[63,111,120,141,151],"aforementioned":[64],"problem":[66],"through":[67],"bidirectional":[68],"adaptation":[69],"both":[71],"Multi-Hierarchy":[72],"Vision":[73],"Adapter":[74],"(MHVA)":[75],"and":[76,97,117,126],"Implicit":[77],"Prompt":[78],"Tuning":[79],"(IPT).":[80],"way,":[83],"our":[84,147],"approach":[85],"requires":[86],"simple":[89],"binary":[90],"prompt":[91],"efficiently":[93],"accomplish":[94],"classification":[96],"tasks":[99],"zero-shot":[101],"scenarios.":[102],"Furthermore,":[103],"introduce":[105],"its":[106],"few-shot":[107],"extension,":[108],"SimCLIP+,":[109],"integrating":[110],"relational":[112],"information":[113,123],"among":[114],"embeddings":[116],"skillfully":[118],"merging":[119],"cross-modal":[121],"synergy":[122],"between":[124],"address":[129],"downstream":[130],"Extensive":[134],"experiments":[135],"two":[137],"challenging":[138],"datasets":[139],"prove":[140],"more":[142],"remarkable":[143],"generalization":[144],"capacity":[145],"method":[148],"compared":[149],"current":[152],"SOTA":[153],"approaches.":[154],"Our":[155],"code":[156],"is":[157],"available":[158],"at":[159],"https://github.com/CH-ORGI/SimCLIP.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}