{"id":"https://openalex.org/W7164856652","doi":"https://doi.org/10.1145/3805622.3810880","title":"Where & What Anomaly? A Framework for Pose-Agnostic Anomaly Detection and Zero-Shot Semantic Classification","display_name":"Where & What Anomaly? A Framework for Pose-Agnostic Anomaly Detection and Zero-Shot Semantic Classification","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164856652","doi":"https://doi.org/10.1145/3805622.3810880"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810880","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810880","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/10.1145/3805622.3810880","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090196409","display_name":"Zhaokun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaokun Huang","raw_affiliation_strings":["Xi\u2019an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0002-7992-5390","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110814145","display_name":"Yonghong Song","orcid":"https://orcid.org/0000-0001-5978-3781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Song","raw_affiliation_strings":["Xi\u2019an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-5978-3781","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085203895","display_name":"H L Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heyao Zhang","raw_affiliation_strings":["Xi\u2019an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0008-7606-3493","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.95069417,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"884","last_page":"892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9476000070571899,"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":0.9476000070571899,"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":0.00559999980032444,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.004999999888241291,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7946000099182129},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5579000115394592},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5564000010490417},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5306000113487244},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4032999873161316},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.38850000500679016},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.36469998955726624},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.3601999878883362},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34610000252723694}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7946000099182129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386000156402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.682200014591217},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5564000010490417},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.38850000500679016},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34940001368522644},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C34872919","wikidata":"https://www.wikidata.org/wiki/Q7092302","display_name":"One-class classification","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810880","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810880","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:10.1145/3805622.3810880","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810880","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W4200150166","https://openalex.org/W4385318467","https://openalex.org/W4386065385","https://openalex.org/W4390874575","https://openalex.org/W4393147759","https://openalex.org/W4393158476","https://openalex.org/W4402716302","https://openalex.org/W4402716375","https://openalex.org/W4402733578","https://openalex.org/W4402916606","https://openalex.org/W4403780904","https://openalex.org/W4403791885","https://openalex.org/W4411631889","https://openalex.org/W4413144266","https://openalex.org/W4413156682","https://openalex.org/W4415537805","https://openalex.org/W4415798746","https://openalex.org/W7133224946","https://openalex.org/W7160068657"],"related_works":[],"abstract_inverted_index":{"Industrial":[0],"anomaly":[1,29,40,133],"detection":[2,30,134],"is":[3,41,45],"commonly":[4],"formulated":[5],"as":[6],"a":[7,23,53,60,101],"binary":[8],"classification":[9,146],"task,":[10],"providing":[11],"limited":[12],"semantic":[13,32],"understanding":[14],"for":[15,27,64],"real-world":[16],"inspection.":[17],"In":[18],"this":[19],"work,":[20],"we":[21,79],"propose":[22],"zero-shot,":[24],"pose-agnostic":[25,54,132],"framework":[26],"fine-grained":[28,144],"and":[31,42,87,112,140,154],"classification,":[33],"capable":[34],"of":[35,76],"answering":[36],"both":[37,152],"where":[38],"the":[39,72,91,126],"what":[43],"it":[44],"without":[46],"defect-specific":[47],"training":[48],"data.":[49],"Our":[50],"approach":[51],"leverages":[52],"3D":[55],"Gaussian":[56],"Splatting":[57],"reference":[58],"with":[59],"SAM-guided":[61],"ROI":[62],"Predictor":[63],"robust":[65],"alignment":[66],"under":[67],"varying":[68],"viewpoints.":[69],"To":[70],"overcome":[71],"global\u2013local":[73],"granularity":[74],"mismatch":[75],"vision\u2013language":[77,156],"models,":[78],"introduce":[80],"Visual\u2013Language":[81],"Differential":[82],"Alignment,":[83],"which":[84],"aligns":[85],"visual":[86],"textual":[88],"residuals":[89],"in":[90,137],"CLIP":[92],"feature":[93],"space":[94],"to":[95],"capture":[96],"subtle":[97],"defect":[98,145],"differences.":[99],"Moreover,":[100],"lightweight":[102],"Multimodal":[103],"Large":[104],"Language":[105],"Model":[106],"dynamically":[107],"generates":[108],"ROI-conditioned,":[109],"anomaly-aware":[110],"hypotheses,":[111],"geometric":[113],"priors":[114],"from":[115,122],"Depth":[116],"Anything":[117],"help":[118],"disambiguate":[119],"texture":[120],"artifacts":[121],"structural":[123],"defects.":[124],"On":[125],"LEGO":[127],"benchmark,":[128],"our":[129],"method":[130],"improves":[131],"by":[135],"2.4%":[136],"image-level":[138],"AUROC":[139],"achieves":[141],"74.7%":[142],"zero-shot":[143],"accuracy,":[147],"demonstrating":[148],"consistent":[149],"gains":[150],"over":[151],"geometry-based":[153],"large-scale":[155],"baselines.":[157]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}