{"id":"https://openalex.org/W7220650657","doi":"https://doi.org/10.48550/arxiv.2610.05129","title":"Representation--Behavior Alignment for Explainable Weakly-Supervised Video Anomaly Detection","display_name":"Representation--Behavior Alignment for Explainable Weakly-Supervised Video Anomaly Detection","publication_year":2026,"publication_date":"2026-10-04","ids":{"openalex":"https://openalex.org/W7220650657","doi":"https://doi.org/10.48550/arxiv.2610.05129"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.05129","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05129","pdf_url":"https://arxiv.org/pdf/2610.05129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.05129","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157736716","display_name":"Chao Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Chao","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101506669","display_name":"Pengfei Wei","orcid":"https://orcid.org/0000-0001-8093-0803","observed_orcids":["https://orcid.org/0000-0001-8093-0803"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei, Pengfei","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157697193","display_name":"Kaige Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Kaige","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157688584","display_name":"Chengliang Liu","orcid":null,"observed_orcids":[]},"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":"Liu, Chengliang","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391896","display_name":"Wei William Wang","orcid":"https://orcid.org/0000-0002-1717-5785","observed_orcids":["https://orcid.org/0000-0002-1717-5785","https://orcid.org/0000-0001-8676-1190","https://orcid.org/0000-0002-0307-0296","https://orcid.org/0000-0002-5987-738X","https://orcid.org/0000-0002-1102-1777","https://orcid.org/0000-0002-9325-3677","https://orcid.org/0000-0001-8980-2680","https://orcid.org/0000-0002-8598-0831","https://orcid.org/0000-0001-5873-2384"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Wei","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132603695","display_name":"Wenqi Ren","orcid":"https://orcid.org/0000-0001-5481-653X","observed_orcids":["https://orcid.org/0000-0001-5481-653X"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren, Wenqi","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157672016","display_name":"Xiaochun Cao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cao, Xiaochun","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9872999787330627,"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":0.9872999787330627,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.007000000216066837,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.000699999975040555,"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/video-anomaly-detection","display_name":"video anomaly detection","score":0.9850000143051147},{"id":"https://openalex.org/keywords/weakly-supervised-learning","display_name":"weakly supervised learning","score":0.843999981880188},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9409999847412109},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.7699999809265137},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.38100001215934753},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.7649999856948853},{"id":"https://openalex.org/keywords/hidden-state-representations","display_name":"hidden state representations","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9394000172615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239999771118164},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6589999794960022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6445000171661377},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6233000159263611},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5546000003814697},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3727000057697296},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28209999203681946}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.05129","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05129","pdf_url":"https://arxiv.org/pdf/2610.05129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.05129","doi":"https://doi.org/10.48550/arxiv.2610.05129","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.05129","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.05129","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05129","pdf_url":"https://arxiv.org/pdf/2610.05129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220650657.pdf","grobid_xml":"https://content.openalex.org/works/W7220650657.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2529194139","https://openalex.org/W2908510526","https://openalex.org/W3168867926","https://openalex.org/W4310926773","https://openalex.org/W4327526719","https://openalex.org/W4387355345","https://openalex.org/W6891822422","https://openalex.org/W7077911270","https://openalex.org/W7131459962","https://openalex.org/W7167071757","https://openalex.org/W7167087659"],"related_works":["https://openalex.org/W7133202329","https://openalex.org/W4390833235","https://openalex.org/W4414587386","https://openalex.org/W4417010403","https://openalex.org/W7167071757","https://openalex.org/W4414880188","https://openalex.org/W7092283269","https://openalex.org/W7160237119","https://openalex.org/W7161309751","https://openalex.org/W7151947918"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"provide":[5],"a":[6,46,60,122,169],"natural":[7],"way":[8],"to":[9,37],"make":[10],"video":[11,81],"anomaly":[12,82,164],"detection":[13,83],"more":[14],"explainable.":[15],"However,":[16],"their":[17,30],"final":[18],"decisions":[19,165],"do":[20],"not":[21],"always":[22],"fully":[23],"use":[24],"the":[25,56,65,69,72,88,138,154],"discriminative":[26,51,159],"information":[27,52],"contained":[28],"in":[29,101],"hidden":[31],"states,":[32],"an":[33],"issue":[34],"we":[35,117],"refer":[36],"as":[38],"representation--behavior":[39],"misalignment.":[40],"We":[41],"decompose":[42],"this":[43],"gap":[44],"into":[45,55],"capacity":[47],"component":[48,62,90],"that":[49,63,77,96,125,146],"measures":[50,64],"never":[53],"aggregated":[54],"readout":[57],"position,":[58],"and":[59,71,85,92,151,161,166],"directional":[61,89],"angular":[66],"mismatch":[67],"between":[68],"optimal":[70],"native":[73],"normal--abnormal":[74],"axis":[75],"at":[76],"position.":[78],"Across":[79],"multiple":[80],"benchmarks":[84,144],"MLLM":[86],"backbones":[87],"dominates,":[91],"residual-stream":[93],"tracing":[94],"shows":[95],"native-axis":[97],"separability":[98],"rises":[99],"sharply":[100],"several":[102],"mid-to-late":[103],"attention":[104,112],"layers.":[105],"Because":[106],"both":[107],"components":[108],"are":[109],"governed":[110],"by":[111],"rather":[113],"than":[114],"MLP":[115],"updates,":[116],"propose":[118],"Representation--Behavior":[119],"Alignment":[120],"(RBA),":[121],"parameter-efficient":[123],"method":[124],"adapts":[126],"those":[127],"layers":[128],"using":[129],"video-level":[130],"labels":[131],"alone":[132],"while":[133],"updating":[134],"about":[135],"0.012\\%":[136],"of":[137],"backbone":[139],"parameters.":[140],"Experiments":[141],"on":[142],"three":[143],"show":[145],"RBA":[147],"improves":[148],"native-readout":[149],"performance":[150],"better":[152],"aligns":[153],"model's":[155],"decision":[156],"direction":[157],"with":[158],"representations,":[160],"it":[162],"produces":[163],"explanations":[167],"through":[168],"single":[170],"generative":[171],"process.":[172]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}