{"id":"https://openalex.org/W4408352761","doi":"https://doi.org/10.1109/icassp49660.2025.10889575","title":"Multi-level Feature Adaptation and Embeddings Alignment for Zero-shot Anomaly Detection","display_name":"Multi-level Feature Adaptation and Embeddings Alignment for Zero-shot Anomaly Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352761","doi":"https://doi.org/10.1109/icassp49660.2025.10889575"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100770760","display_name":"Yiqing Liu","orcid":"https://orcid.org/0000-0002-8157-2814"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiqing Liu","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,HeFei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,HeFei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107518903","display_name":"Huilin Deng","orcid":"https://orcid.org/0009-0003-8944-1135"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huilin Deng","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,HeFei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,HeFei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090469219","display_name":"Gang Zhao","orcid":"https://orcid.org/0000-0002-5355-4336"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Zhao","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,HeFei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,HeFei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100770760"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.8599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89824781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9819999933242798,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9713000059127808,"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/computer-science","display_name":"Computer science","score":0.6402928233146667},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6224743127822876},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5922760963439941},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5496769547462463},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.540375828742981},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5277196764945984},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5063871145248413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5005075931549072},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4580193758010864},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.45457690954208374},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14497581124305725},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.07847738265991211},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05735182762145996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6402928233146667},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6224743127822876},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5922760963439941},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5496769547462463},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.540375828742981},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5277196764945984},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5063871145248413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5005075931549072},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4580193758010864},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.45457690954208374},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14497581124305725},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.07847738265991211},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05735182762145996},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2008359794","https://openalex.org/W2948982773","https://openalex.org/W2963946669","https://openalex.org/W3090449556","https://openalex.org/W3147184966","https://openalex.org/W3198377975","https://openalex.org/W4312605624","https://openalex.org/W4312772600","https://openalex.org/W4386065385","https://openalex.org/W4402703054","https://openalex.org/W4402716375","https://openalex.org/W4402917235","https://openalex.org/W4404420613","https://openalex.org/W4404612908","https://openalex.org/W6791353385","https://openalex.org/W6811013733","https://openalex.org/W6838461383","https://openalex.org/W6851740254","https://openalex.org/W6853095873","https://openalex.org/W6856244187","https://openalex.org/W6858057904","https://openalex.org/W6965410735"],"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],"(AD)":[2],"is":[3],"an":[4,94],"important":[5],"and":[6,40,79,96,116],"challenging":[7],"task":[8],"in":[9,22],"computer":[10],"vision.":[11],"Recently,":[12],"Contrastive":[13],"Language-Image":[14],"Pre-training":[15],"(CLIP)":[16],"has":[17],"shown":[18],"impressive":[19],"generalization":[20],"capability":[21],"zero-shot":[23],"AD":[24,89],"tasks.":[25],"However,":[26],"the":[27,41,70,74,112,123],"inherent":[28],"global":[29],"semantic":[30,58,82],"consistency":[31],"of":[32,43,77,125],"CLIP":[33],"fails":[34],"to":[35,47,63,88,101,108],"accurately":[36],"identify":[37],"subtle":[38,78],"anomalies,":[39],"lack":[42],"fine-grained":[44],"alignment":[45,95],"leads":[46],"inaccurate":[48],"defect":[49],"localization.":[50],"In":[51],"this":[52],"study,":[53],"we":[54],"propose":[55],"a":[56],"hierarchical":[57],"feature":[59],"adaptation":[60,87],"framework":[61],"designed":[62],"better":[64],"leverage":[65],"intermediate":[66],"layer":[67],"information":[68],"from":[69,106],"visual":[71,115],"encoder,":[72],"enabling":[73],"effective":[75],"capture":[76],"diverse":[80],"anomaly-aware":[81],"features,":[83],"thus":[84],"improving":[85],"CLIP\u2019s":[86],"task.":[90],"We":[91],"further":[92],"introduce":[93],"mask":[97],"refinement":[98],"co-optimization":[99],"decoder":[100],"locate":[102],"key":[103],"anomalous":[104],"regions":[105],"coarse":[107],"fine,":[109],"thereby":[110],"alleviating":[111],"misalignment":[113],"between":[114],"textual":[117],"embeddings.":[118],"The":[119],"experimental":[120],"results":[121],"demonstrate":[122],"effectiveness":[124],"our":[126],"method.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
