{"id":"https://openalex.org/W4416512840","doi":"https://doi.org/10.1109/iccv51701.2025.01121","title":"Autoregressive Denoising Score Matching Is a Good Video Anomaly Detector","display_name":"Autoregressive Denoising Score Matching Is a Good Video Anomaly Detector","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416512840","doi":"https://doi.org/10.1109/iccv51701.2025.01121"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.23282","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100332171","display_name":"Hanwen Zhang","orcid":"https://orcid.org/0000-0001-6712-1972"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanwen Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013382259","display_name":"Congqi Cao","orcid":"https://orcid.org/0000-0002-0217-9791"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congqi Cao","raw_affiliation_strings":["Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015584209","display_name":"Qinyi Lv","orcid":"https://orcid.org/0000-0002-5359-5701"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinyi Lv","raw_affiliation_strings":["Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058520218","display_name":"Lingtong Min","orcid":"https://orcid.org/0000-0003-3970-7823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingtong Min","raw_affiliation_strings":["Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103564469","display_name":"Zhang Yanning","orcid":"https://orcid.org/0009-0003-5848-3252"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanning Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi'an,Shaanxi,China,710129","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100332171"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17976723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12057","last_page":"12067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9731000065803528,"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":0.9731000065803528,"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":0.004999999888241291,"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/T11439","display_name":"Video Analysis and Summarization","score":0.003100000089034438,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5306000113487244},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.51910001039505},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.47530001401901245},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.460099995136261},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.388700008392334},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.38670000433921814},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.36970001459121704},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.36719998717308044},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.3547999858856201}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6496999859809875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5485000014305115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.388700008392334},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.38670000433921814},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C2777708103","wikidata":"https://www.wikidata.org/wiki/Q852589","display_name":"Motion blur","level":3,"score":0.3303000032901764},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2980000078678131},{"id":"https://openalex.org/C65660741","wikidata":"https://www.wikidata.org/wiki/Q3952743","display_name":"Score","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.23282","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23282","pdf_url":"https://arxiv.org/pdf/2506.23282","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.23282","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.23282","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.23282","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23282","pdf_url":"https://arxiv.org/pdf/2506.23282","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"anomaly":[1,199],"detection":[2],"(VAD)":[3],"is":[4,22],"an":[5,179],"important":[6],"computer":[7],"vision":[8],"problem.":[9],"Thanks":[10],"to":[11,42,119,167],"the":[12,19,43,50,95,110,121,149,154,160,164,175,185,208],"mode":[13],"coverage":[14],"capabilities":[15],"of":[16,98,115,123,211],"generative":[17],"models,":[18],"likelihood-based":[20,38],"paradigm":[21],"catching":[23],"growing":[24],"interest,":[25],"as":[26],"it":[27,173],"can":[28,194],"model":[29,103],"normal":[30],"distribution":[31],"and":[32,70,89,104,152,171,183],"detect":[33],"out-of-distribution":[34],"anomalies.":[35],"However,":[36],"these":[37,55],"methods":[39],"are":[40],"blind":[41],"anomalies":[44],"located":[45],"in":[46,65,125],"local":[47],"modes":[48],"near":[49],"learned":[51],"distribution.":[52],"To":[53],"handle":[54],"``unseen\"":[56],"anomalies,":[57],"we":[58,73,85,127,158,193],"dive":[59],"into":[60,101,148],"three":[61,190,203],"gaps":[62,191],"uniquely":[63],"existing":[64],"VAD":[66,205],"regarding":[67],"scene,":[68],"motion":[69,106],"appearance.":[71],"Specifically,":[72],"first":[74],"build":[75],"a":[76,87,133,169,196],"noise-conditioned":[77],"score":[78,82,91,137,156,176],"transformer":[79],"for":[80,140,178],"denoising":[81,136],"matching.":[83],"Then,":[84],"introduce":[86],"scene-dependent":[88],"motion-aware":[90],"function":[92,177],"by":[93],"embedding":[94],"scene":[96],"condition":[97],"input":[99,116],"sequences":[100],"our":[102,212],"assigning":[105],"weights":[107],"based":[108],"on":[109,202],"difference":[111,170],"between":[112],"key":[113],"frames":[114],"sequences.":[117],"Next,":[118],"solve":[120],"problem":[122],"blindness":[124],"principle,":[126],"integrate":[128],"unaffected":[129],"visual":[130],"information":[131],"via":[132],"novel":[134],"autoregressive":[135],"matching":[138],"mechanism":[139],"inference.":[141],"Through":[142],"autoregressively":[143],"injecting":[144],"intensifying":[145],"Gaussian":[146],"noise":[147],"denoised":[150,161],"data":[151,162,166],"estimating":[153],"corresponding":[155],"function,":[157],"compare":[159],"with":[163,174],"original":[165],"get":[168],"aggregate":[172],"enhanced":[180],"appearance":[181],"perception":[182],"accumulate":[184],"abnormal":[186],"context.":[187],"With":[188],"all":[189],"considered,":[192],"compute":[195],"more":[197],"comprehensive":[198],"indicator.":[200],"Experiments":[201],"popular":[204],"benchmarks":[206],"demonstrate":[207],"state-of-the-art":[209],"performance":[210],"method.":[213]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}