{"id":"https://openalex.org/W4415536772","doi":"https://doi.org/10.1145/3746027.3755422","title":"UniAD: Integrating Geometric and Semantic Cues for Unified Anomaly Detection","display_name":"UniAD: Integrating Geometric and Semantic Cues for Unified Anomaly Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536772","doi":"https://doi.org/10.1145/3746027.3755422"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5100382689","display_name":"Xiaodong Wang","orcid":"https://orcid.org/0000-0002-9153-1928"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["Xiamen University of Technology, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112483258","display_name":"H L Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongmin Hu","raw_affiliation_strings":["Xiamen University of Technology, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111509913","display_name":"Fei Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yan","raw_affiliation_strings":["Xiamen University of Technology, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036720049","display_name":"Junwen Lu","orcid":"https://orcid.org/0000-0002-7098-2789"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwen Lu","raw_affiliation_strings":["Xiamen University of Technology, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102802663","display_name":"Zhiqiang Zeng","orcid":"https://orcid.org/0000-0001-9716-1182"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Zeng","raw_affiliation_strings":["Xiamen University of Technology, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103517296","display_name":"Weidong Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Hong","raw_affiliation_strings":["Xiamen Truesight Technology Co., Ltd, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen Truesight Technology Co., Ltd, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034162160","display_name":"Zhedong Zheng","orcid":"https://orcid.org/0000-0002-2434-9050"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Zhedong Zheng","raw_affiliation_strings":["University of Macau, Macau, China"],"affiliations":[{"raw_affiliation_string":"University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100382689"],"corresponding_institution_ids":["https://openalex.org/I75867142"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16311051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4408","last_page":"4417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"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":1.0,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9860000014305115,"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":0.7160000205039978},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6880999803543091},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5763999819755554},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5695000290870667},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5601999759674072},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5260000228881836},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.47600001096725464},{"id":"https://openalex.org/keywords/logical-consequence","display_name":"Logical consequence","score":0.4596000015735626},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.42820000648498535}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7160000205039978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110999822616577},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6880999803543091},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5763999819755554},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5695000290870667},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5601999759674072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5331000089645386},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C203702819","wikidata":"https://www.wikidata.org/wiki/Q17146953","display_name":"Logical data model","level":3,"score":0.3813999891281128},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.290800005197525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.26409998536109924}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2948982773","https://openalex.org/W3034314048","https://openalex.org/W3109715690","https://openalex.org/W3159481202","https://openalex.org/W3169651898","https://openalex.org/W4212874935","https://openalex.org/W4304091765","https://openalex.org/W4366493107","https://openalex.org/W4386065890","https://openalex.org/W4386632296","https://openalex.org/W4393147759","https://openalex.org/W4393154102","https://openalex.org/W4394625793","https://openalex.org/W4394625802","https://openalex.org/W4401284370","https://openalex.org/W4407800509"],"related_works":[],"abstract_inverted_index":{"Current":[0],"anomaly":[1,30,43,155],"detection":[2,44],"paradigms":[3],"face":[4],"inherent":[5],"limitations":[6],"in":[7,77],"simultaneously":[8],"addressing":[9],"structural":[10,74,122,197],"anomalies":[11,17,192],"(\\eg,":[12,18],"geometric":[13,175],"distortions)":[14],"and":[15,80,110,177,193],"logical":[16,83,132,150,191],"semantic":[19,128,143,178],"inconsistencies),":[20],"due":[21],"to":[22,152,172],"conflicting":[23],"feature":[24,95,118],"representation":[25],"requirements":[26,56],"between":[27],"these":[28],"two":[29,66,111],"categories.":[31],"We":[32],"propose":[33],"UniAD,":[34],"a":[35,73,82,147],"novel":[36],"dual-branch":[37],"teacher-student":[38],"framework":[39,64],"that":[40,166],"achieves":[41],"unified":[42],"through":[45,134],"synergistic":[46],"integration":[47],"of":[48,57,149,169],"complementary":[49,99],"expertise":[50],"from":[51],"heterogeneous":[52],"vision":[53],"models":[54,69],"without":[55],"extra":[58],"manual":[59],"annotations.":[60],"In":[61],"particular,":[62],"our":[63,170],"integrates":[65],"frozen":[67],"expert":[68],"as":[70,146],"teachers:":[71],"(1)":[72],"teacher":[75,84,123,133],"specializing":[76],"geometric-sensitive":[78],"patterns,":[79],"(2)":[81],"focusing":[85],"on":[86,159],"semantic-aware":[87],"representations":[88],"via":[89],"component":[90],"relationship":[91],"modeling.":[92],"To":[93],"resolve":[94],"conflicts":[96],"while":[97,124],"preserving":[98],"information,":[100],"the":[101,121,131,141,154,160,167],"student":[102],"network":[103],"is":[104],"equipped":[105],"with":[106,120,130],"one":[107],"shared":[108],"backbone":[109],"independent":[112],"branches.":[113],"One":[114],"branch":[115,126],"employs":[116],"multi-scale":[117],"alignment":[119],"another":[125],"establishing":[127],"correspondence":[129],"component-aware":[135],"attention":[136],"mechanisms.":[137],"Furthermore,":[138],"we":[139],"introduce":[140],"text-guided":[142],"enhancement":[144],"module":[145],"kind":[148],"guidance":[151],"facilitate":[153],"indicator.":[156],"Extensive":[157],"experiments":[158],"challenging":[161],"MVTec":[162],"LOCO":[163],"benchmark":[164],"validate":[165],"scalability":[168],"model":[171],"localize":[173],"both":[174],"distortions":[176],"inconsistencies.":[179],"The":[180],"proposed":[181],"method":[182],"outperforms":[183],"existing":[184],"single-purpose":[185],"detectors,":[186],"yielding":[187],"93.7%":[188],"AUROC":[189,195],"for":[190,196],"93.2%":[194],"anomalies.":[198]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}