{"id":"https://openalex.org/W7164810521","doi":"https://doi.org/10.1145/3805622.3810745","title":"SSHF-CLIP: Semantic-Guided Scale Selection and Hybrid Fusion for Zero-Shot Anomaly Detection","display_name":"SSHF-CLIP: Semantic-Guided Scale Selection and Hybrid Fusion for Zero-Shot Anomaly Detection","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164810521","doi":"https://doi.org/10.1145/3805622.3810745"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810745","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810745","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128360392","display_name":"Kaiyuan Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyuan Jin","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0008-0914-6184","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056052658","display_name":"Wayit Abliz","orcid":"https://orcid.org/0000-0002-6903-5311"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wayit Abliz","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-6903-5311","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083019855","display_name":"Maihemuti Maimaiti","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maihemuti Maimaiti","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0001-9225-0554","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061296090","display_name":"Zaokere Kadeer","orcid":"https://orcid.org/0000-0001-9475-1101"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zaokere Kadeer","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0001-9475-1101","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077794475","display_name":"Aishan Wumaier","orcid":"https://orcid.org/0000-0003-1681-1089"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aishan Wumaier","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-1681-1089","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049065526","display_name":"Abdujelil Abdurahman","orcid":"https://orcid.org/0000-0003-2248-4678"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Abdujelil Abdurahman","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-2248-4678","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100643514","display_name":"Panpan Zheng","orcid":"https://orcid.org/0009-0003-2934-6339"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panpan Zheng","raw_affiliation_strings":["Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0003-2934-6339","affiliations":[{"raw_affiliation_string":"Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94655426,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"654","last_page":"662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9218000173568726,"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":0.9218000173568726,"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":0.036400001496076584,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.003800000064074993,"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":0.7046999931335449},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5421000123023987},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4797999858856201},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45239999890327454},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4341999888420105},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4189999997615814},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4156000018119812},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4104999899864197},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.39959999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7080000042915344},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7046999931335449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5993000268936157},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5421000123023987},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4341999888420105},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4302000105381012},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3765999972820282},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3158999979496002},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810745","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810745","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6108169555664062}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2008359794","https://openalex.org/W2623808523","https://openalex.org/W2890165066","https://openalex.org/W2943666912","https://openalex.org/W2963523189","https://openalex.org/W3008932301","https://openalex.org/W3092704883","https://openalex.org/W3093545390","https://openalex.org/W3147184966","https://openalex.org/W3168175245","https://openalex.org/W3169651898","https://openalex.org/W3183588514","https://openalex.org/W3198377975","https://openalex.org/W3209793239","https://openalex.org/W4206411775","https://openalex.org/W4285241348","https://openalex.org/W4312605624","https://openalex.org/W4312772600","https://openalex.org/W4386065385","https://openalex.org/W4386065608","https://openalex.org/W4386065890","https://openalex.org/W4386075837","https://openalex.org/W4394597908","https://openalex.org/W4402703054","https://openalex.org/W4402917235","https://openalex.org/W4409264050","https://openalex.org/W4413156682","https://openalex.org/W4415540103","https://openalex.org/W7133225595"],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"anomaly":[1,48],"detection":[2,166],"(ZSAD)":[3],"aims":[4],"to":[5,106,117],"identify":[6],"anomalies":[7],"in":[8],"unseen":[9],"domains":[10],"(e.g.,":[11],"industrial":[12],"or":[13],"medical":[14,182],"imagery)":[15],"by":[16,31,55,112,143],"leveraging":[17],"pre-trained":[18],"vision-language":[19],"models":[20],"like":[21],"CLIP.":[22],"However,":[23],"the":[24,35,40,51,56,119,123,146,163],"direct":[25],"application":[26],"of":[27],"CLIP":[28],"is":[29],"impeded":[30],"two":[32],"critical":[33],"challenges:":[34],"feature":[36],"misalignment":[37],"arising":[38],"from":[39,154],"discrepancy":[41],"between":[42,59,165],"fixed":[43],"receptive":[44],"fields":[45],"and":[46,50,63,82,93,133,168,181],"diverse":[47,197],"scales,":[49],"decision":[52],"ambiguity":[53],"caused":[54],"inherent":[57],"conflict":[58],"global":[60,147],"semantic":[61,148],"coherence":[62],"local":[64,151],"defect":[65],"sensitivity.":[66],"To":[67],"tackle":[68],"these":[69],"issues,":[70],"we":[71],"propose":[72],"SSHF-CLIP,":[73],"a":[74,87,94,102,113,140,155],"novel":[75],"framework":[76],"that":[77,185],"unifies":[78],"Semantic-Guided":[79,88],"Scale":[80,89],"Selection":[81,90],"Hybrid":[83],"Fusion.":[84],"SSHF-CLIP":[85,186],"integrates":[86],"(SGSS)":[91],"module":[92],"Global-Semantic":[95],"Fusion":[96],"Module":[97],"(GSFM).":[98],"SGSS":[99],"first":[100],"employs":[101],"semantic-driven":[103],"gating":[104],"mechanism":[105],"adaptively":[107],"reweight":[108],"multi-scale":[109],"representations,":[110],"followed":[111],"learnable":[114],"projection":[115],"transformation":[116],"align":[118],"aggregated":[120],"features":[121],"with":[122,149],"textual":[124],"embedding":[125],"space.":[126],"This":[127],"design":[128],"effectively":[129,161],"suppresses":[130],"background":[131],"noise":[132],"captures":[134],"structure-critical":[135],"anomalies.":[136],"Furthermore,":[137],"GSFM":[138],"implements":[139],"discrepancy-aware":[141],"strategy":[142],"dynamically":[144],"calibrating":[145],"fine-grained":[150],"semantics":[152],"mined":[153],"Local":[156],"Anomaly":[157],"Feature":[158],"Extractor":[159],"(LAFE),":[160],"resolving":[162],"trade-off":[164],"sensitivity":[167],"false":[169],"positive":[170],"suppression.":[171],"Extensive":[172],"experiments":[173],"on":[174],"eight":[175,189],"benchmarks":[176],"(including":[177],"MVTec":[178],"AD,":[179],"VisA,":[180],"datasets)":[183],"demonstrate":[184],"significantly":[187],"outperforms":[188],"state-of-the-art":[190],"methods,":[191],"achieving":[192],"superior":[193],"zero-shot":[194],"generalization":[195],"across":[196],"domains.":[198]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}