{"id":"https://openalex.org/W4414432329","doi":"https://doi.org/10.1109/case58245.2025.11163751","title":"EVT-CLIP: Enhancing Zero-Shot Anomaly Segmentation with Vision-Text Models","display_name":"EVT-CLIP: Enhancing Zero-Shot Anomaly Segmentation with Vision-Text Models","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414432329","doi":"https://doi.org/10.1109/case58245.2025.11163751"},"language":"en","primary_location":{"id":"doi:10.1109/case58245.2025.11163751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","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/A5100333777","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0003-1027-7700"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhijian Yue","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045934908","display_name":"Zhen Shen","orcid":"https://orcid.org/0000-0002-9634-4945"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Shen","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002055863","display_name":"Qihang Fang","orcid":"https://orcid.org/0000-0003-1438-0094"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihang Fang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739965","display_name":"Weixing Wang","orcid":"https://orcid.org/0000-0001-9415-1560"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixing Wang","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088979194","display_name":"Gang Xiong","orcid":"https://orcid.org/0000-0002-4303-5559"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Xiong","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101115181","display_name":"Xisong Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xisong Dong","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113600509","display_name":"Fei\u2010Yue Wang","orcid":"https://orcid.org/0000-0001-9185-3989"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei-Yue Wang","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory for Management and Control of Complex Systems, Institute of Automation,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory for Management and Control of Complex Systems, Institute of Automation,Beijing,China,100190","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100333777"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14194642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"643","last_page":"649"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9742000102996826,"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/T10028","display_name":"Topic Modeling","score":0.9742000102996826,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9122999906539917,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7110000252723694},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.6876000165939331},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6743000149726868},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6723999977111816},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6604999899864197},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4941999912261963},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47760000824928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239999771118164},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7110000252723694},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.6876000165939331},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6743000149726868},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6723999977111816},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6604999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5982999801635742},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4415999948978424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38370001316070557},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2971999943256378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29319998621940613},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case58245.2025.11163751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"zero-shot":[3],"anomaly":[4,20,34,88,149,201],"segmentation":[5,202],"(ZSAS)":[6],"has":[7],"emerged":[8],"as":[9],"a":[10],"cutting-edge":[11],"technology,":[12],"demonstrating":[13],"significant":[14],"potential":[15],"in":[16,51,62,74,163,200,214],"the":[17,38,52,85,102,109,116,125,144,152,193],"field":[18],"of":[19,44,56,87,96],"detection.":[21],"However,":[22],"traditional":[23],"methods":[24,48,207],"often":[25],"rely":[26],"on":[27,130,187],"manually":[28],"designed":[29],"fixed":[30],"textual":[31,140],"descriptions":[32],"or":[33],"prompts,":[35,141],"which":[36],"limits":[37],"model\u2019s":[39,117,145],"adaptability":[40,146],"to":[41,100,114,147],"different":[42],"types":[43],"anomalies.":[45],"Additionally,":[46],"existing":[47,205],"exhibit":[49],"shortcomings":[50],"interaction":[53,167],"and":[54,58,66,90,120,159,170,176,183,208,212],"fusion":[55],"image":[57,137,169],"text":[59,171,174],"features,":[60,172],"resulting":[61],"suboptimal":[63],"cross-modal":[64,121,179],"understanding":[65,180],"insufficient":[67],"information":[68,122,132,162],"sharing.":[69],"To":[70],"address":[71],"these":[72],"challenges,":[73],"this":[75,97],"paper":[76],"we":[77],"propose":[78],"an":[79],"innovative":[80],"ZSAS":[81,206],"method\u2014EVT-CLIP\u2014aimed":[82],"at":[83],"enhancing":[84,143],"performance":[86,198],"detection":[89],"localization":[91],"tasks.":[92],"The":[93],"core":[94],"idea":[95],"method":[98],"is":[99],"combine":[101],"Dynamic":[103],"Attention-Enhanced":[104],"Prompt":[105],"(DAEP)":[106],"module":[107,113,127,154],"with":[108,139],"Cross-modal":[110],"Interaction":[111],"(CMI)":[112],"improve":[115],"generalization":[118],"capability":[119],"fusion.":[123],"Specifically,":[124],"DAEP":[126],"reduces":[128],"reliance":[129],"category-specific":[131],"by":[133],"precisely":[134],"fusing":[135],"global":[136,160],"features":[138],"thereby":[142],"various":[148],"types.":[150],"Meanwhile,":[151],"CMI":[153],"captures":[155],"both":[156],"local":[157],"details":[158],"contextual":[161],"images":[164,182],"through":[165],"deep":[166],"between":[168,181],"optimizes":[173],"embeddings,":[175],"significantly":[177],"enhances":[178],"text.":[184],"Experimental":[185],"validation":[186],"multiple":[188],"benchmark":[189],"datasets":[190],"demonstrates":[191],"that":[192],"EVT-CLIP":[194],"framework":[195],"achieves":[196],"remarkable":[197],"improvements":[199],"tasks,":[203],"outperforming":[204],"proving":[209],"its":[210],"effectiveness":[211],"advantages":[213],"practical":[215],"applications.":[216]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}