{"id":"https://openalex.org/W4416159174","doi":"https://doi.org/10.1109/wacv61042.2026.00705","title":"VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models","display_name":"VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416159174","doi":"https://doi.org/10.1109/wacv61042.2026.00705"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.07299","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102253899","display_name":"Ying Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying Cheng","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu-Ho Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ho Lin","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075373716","display_name":"Min-Hung Chen","orcid":"https://orcid.org/0000-0002-4046-3937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min-Hung Chen","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032964198","display_name":"Fu-En Yang","orcid":"https://orcid.org/0000-0003-0102-7101"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu-En Yang","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073849580","display_name":"Shang\u2010Hong Lai","orcid":"https://orcid.org/0000-0002-5092-993X"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shang-Hong Lai","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7301","last_page":"7311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9258999824523926,"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":0.9258999824523926,"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":0.028300000354647636,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.005100000184029341,"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/anomaly-detection","display_name":"Anomaly detection","score":0.5936999917030334},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5636000037193298},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5336999893188477},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.48030000925064087},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4763999879360199},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.46549999713897705},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.453000009059906},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.44359999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962000131607056},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5936999917030334},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5512999892234802},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5336999893188477},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41769999265670776},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2524999976158142},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.07299","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.07299","pdf_url":"https://arxiv.org/pdf/2511.07299","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.07299","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.07299","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.07299","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.07299","pdf_url":"https://arxiv.org/pdf/2511.07299","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":"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":[0,60],"anomaly":[1,74,88,162,175],"understanding":[2,47],"(VAU)":[3],"aims":[4],"to":[5,72,85,97,137],"provide":[6],"detailed":[7],"interpretation":[8],"and":[9,27,39,110,130,143,165],"semantic":[10],"comprehension":[11,75],"of":[12,19,102,172],"anomalous":[13,48,104],"events":[14],"within":[15],"videos,":[16],"addressing":[17],"limitations":[18],"traditional":[20],"methods":[21],"that":[22,156],"focus":[23],"solely":[24],"on":[25,150],"detecting":[26],"localizing":[28],"anomalies.":[29],"However,":[30],"existing":[31],"approaches":[32],"often":[33],"neglect":[34],"the":[35,99,170],"deeper":[36],"causal":[37,100,166],"relationships":[38],"interactions":[40],"between":[41],"objects,":[42],"which":[43,63],"are":[44,133],"critical":[45],"for":[46,59,125],"behaviors.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"propose":[54],"VADER,":[55],"an":[56,82],"LLM-driven":[57],"framework":[58],"Anomaly":[61,83],"unDErstanding,":[62],"integrates":[64],"keyframe":[65],"object":[66,119],"Relation":[67,107,113],"features":[68],"with":[69,135],"visual":[70,129],"cues":[71,132],"enhance":[73],"from":[76],"video.":[77],"Specifically,":[78],"VADER":[79,157],"first":[80],"applies":[81],"Scorer":[84],"assign":[86],"per-frame":[87],"scores,":[89],"followed":[90],"by":[91],"a":[92,111],"Context-AwarE":[93],"Sampling":[94],"(CAES)":[95],"strategy":[96],"capture":[98],"context":[101],"each":[103],"event.":[105],"A":[106],"Feature":[108],"Extractor":[109],"COntrastive":[112],"Encoder":[114],"(CORE)":[115],"jointly":[116],"model":[117],"dynamic":[118],"interactions,":[120],"producing":[121],"compact":[122],"relational":[123,131],"representations":[124],"downstream":[126],"reasoning.":[127],"These":[128],"integrated":[134],"LLMs":[136],"generate":[138],"detailed,":[139],"causally":[140],"grounded":[141],"descriptions":[142],"support":[144],"robust":[145],"anomaly-related":[146],"question":[147],"answering.":[148],"Experiments":[149],"multiple":[151],"real-world":[152],"VAU":[153],"benchmarks":[154],"demonstrate":[155],"achieves":[158],"strong":[159],"results":[160],"across":[161],"description,":[163],"explanation,":[164],"reasoning":[167],"tasks,":[168],"advancing":[169],"frontier":[171],"explainable":[173],"video":[174],"analysis.":[176],"Project":[177],"page":[178],"is":[179],"available":[180],"at":[181],"https://vader-vau.github.io/.":[182]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-12T00:00:00"}