{"id":"https://openalex.org/W4411552496","doi":"https://doi.org/10.1109/cscwd64889.2025.11033177","title":"Customizing Visual-Language Foundation Models for Multi-Modal Anomaly Detection and Reasoning","display_name":"Customizing Visual-Language Foundation Models for Multi-Modal Anomaly Detection and Reasoning","publication_year":2025,"publication_date":"2025-05-05","ids":{"openalex":"https://openalex.org/W4411552496","doi":"https://doi.org/10.1109/cscwd64889.2025.11033177"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd64889.2025.11033177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd64889.2025.11033177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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/A5018803784","display_name":"Xiaohao Xu","orcid":"https://orcid.org/0000-0002-6750-9704"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaohao Xu","raw_affiliation_strings":["University of Michigan-Ann Arbor,Robotics Department,Ann Arbor,MI,USA,48105"],"affiliations":[{"raw_affiliation_string":"University of Michigan-Ann Arbor,Robotics Department,Ann Arbor,MI,USA,48105","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044965902","display_name":"Yunkang Cao","orcid":"https://orcid.org/0000-0001-7619-6618"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunkang Cao","raw_affiliation_strings":["School of Mechanical Science and Engineering, Huazhong University of Science and Technology,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034584818","display_name":"Hua\u2010Xin Zhang","orcid":"https://orcid.org/0000-0003-1739-0124"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaxin Zhang","raw_affiliation_strings":["School of Mechanical Science and Engineering, Huazhong University of Science and Technology,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013734579","display_name":"Nong Sang","orcid":"https://orcid.org/0000-0002-9167-1496"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nong Sang","raw_affiliation_strings":["School of Mechanical Science and Engineering, Huazhong University of Science and Technology,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000690549","display_name":"Xiaonan Huang","orcid":"https://orcid.org/0000-0002-2313-1551"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaonan Huang","raw_affiliation_strings":["University of Michigan-Ann Arbor,Robotics Department,Ann Arbor,MI,USA,48105"],"affiliations":[{"raw_affiliation_string":"University of Michigan-Ann Arbor,Robotics Department,Ann Arbor,MI,USA,48105","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018803784"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":8.6528,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97306179,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1443","last_page":"1448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.90829998254776,"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":0.90829998254776,"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/foundation","display_name":"Foundation (evidence)","score":0.6898694634437561},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6690749526023865},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6510387659072876},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.619175374507904},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.4903905391693115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.464415967464447},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38412898778915405}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6898694634437561},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690749526023865},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6510387659072876},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.619175374507904},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.4903905391693115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.464415967464447},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38412898778915405},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd64889.2025.11033177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd64889.2025.11033177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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":9,"referenced_works":["https://openalex.org/W2963795951","https://openalex.org/W3118600296","https://openalex.org/W4212874935","https://openalex.org/W4212919149","https://openalex.org/W4405595839","https://openalex.org/W6784869275","https://openalex.org/W6791353385","https://openalex.org/W6860041859","https://openalex.org/W6873338258"],"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":{"Anomaly":[0],"detection":[1,19,50,134,155,184,214],"is":[2,44,197],"vital":[3],"in":[4,14,32,56],"various":[5],"industrial":[6],"scenarios,":[7],"including":[8,107],"the":[9,18,99,121,151,161,182],"identification":[10],"of":[11,20,124,207],"unusual":[12],"patterns":[13],"production":[15],"lines":[16],"and":[17,35,73,80,114,135,144,175,185,192],"manufacturing":[21],"defects":[22],"for":[23,149,189,211],"quality":[24],"control.":[25],"Existing":[26],"techniques":[27],"tend":[28],"to":[29,45,97,163],"be":[30,54],"specialized":[31],"individual":[33],"scenarios":[34],"lack":[36],"generalization":[37],"capacities.":[38],"In":[39,117],"this":[40],"study,":[41],"our":[42],"objective":[43],"develop":[46],"a":[47,85,127],"generic":[48,64],"anomaly":[49,78,133,154,183,213],"model":[51],"that":[52,69,89,141],"can":[53],"applied":[55],"multiple":[57],"scenarios.":[58],"To":[59],"achieve":[60],"this,":[61],"we":[62,83,119],"custom-build":[63],"visual":[65,143],"language":[66,145],"foundation":[67,209],"models":[68,152,159,210],"possess":[70],"extensive":[71],"knowledge":[72,92],"robust":[74],"reasoning":[75,186],"abilities":[76],"as":[77,95,147,171],"detectors":[79],"reasoners.":[81],"Specifically,":[82],"introduce":[84],"multi-modal":[86,132],"prompting":[87],"strategy":[88],"incorporates":[90],"domain":[91],"from":[93],"experts":[94],"conditions":[96,148],"guide":[98],"models.":[100],"Our":[101,137,195],"approach":[102],"considers":[103],"diverse":[104],"prompt":[105],"types,":[106],"task":[108],"descriptions,":[109],"class":[110],"context,":[111],"normality":[112],"rules,":[113],"reference":[115],"images.":[116],"addition,":[118],"unify":[120],"input":[122],"representation":[123],"multi-modality":[125],"into":[126],"2D":[128],"image":[129],"format,":[130],"enabling":[131],"reasoning.":[136],"preliminary":[138],"studies":[139,179],"demonstrate":[140],"combining":[142],"prompts":[146],"customizing":[150],"enhances":[153],"performance.":[156],"The":[157],"customized":[158,208],"showcase":[160],"ability":[162],"detect":[164],"anomalies":[165],"across":[166],"different":[167],"data":[168],"modalities":[169],"such":[170],"images,":[172],"point":[173],"clouds,":[174],"videos.":[176],"Qualitative":[177],"case":[178],"further":[180],"highlight":[181],"capabilities,":[187],"particularly":[188],"multi-object":[190],"scenes":[191],"temporal":[193],"data.":[194],"code":[196],"publicly":[198],"available":[199,217],"at":[200,218],"https://github.com/Xiaohac-Xu/Customizable-VLM.<sup":[201],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[202,204],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[203],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>More":[205],"insights":[206],"broader":[212],"settings":[215],"are":[216],"Github":[219],"repo:":[220],"https://github.com/caoyunkang/GPT4V-for-Generic-Anomaly-Detection.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}