{"id":"https://openalex.org/W7138191717","doi":"https://doi.org/10.1609/aaai.v40i10.37790","title":"FineVAU: A Novel Human-Aligned Benchmark for Fine-Grained Video Anomaly Understanding","display_name":"FineVAU: A Novel Human-Aligned Benchmark for Fine-Grained Video Anomaly Understanding","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138191717","doi":"https://doi.org/10.1609/aaai.v40i10.37790"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i10.37790","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37790","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i10.37790","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Joao Alexandre Cardeira Pereira","orcid":null},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Joao Alexandre Cardeira Pereira","raw_affiliation_strings":["NOVA LINCS, Lisboa\nNOVA FCT, Lisboa\nDeepNeuronic, Covilh\u00e3"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA LINCS, Lisboa\nNOVA FCT, Lisboa\nDeepNeuronic, Covilh\u00e3","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vasco Lopes","orcid":null},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Vasco Lopes","raw_affiliation_strings":["DeepNeuronic, Covilh\u00e3\nNOVA LINCS, Lisboa\nUniversity of Beira Interior, Covilh\u00e3"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepNeuronic, Covilh\u00e3\nNOVA LINCS, Lisboa\nUniversity of Beira Interior, Covilh\u00e3","institution_ids":["https://openalex.org/I161321875"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jo\u00e3o C. Neves","orcid":null},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o C. Neves","raw_affiliation_strings":["NOVA LINCS, Lisboa\nUniversity of Beira Interior, Covilh\u00e3"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA LINCS, Lisboa\nUniversity of Beira Interior, Covilh\u00e3","institution_ids":["https://openalex.org/I161321875"]}]},{"author_position":"last","author":{"id":null,"display_name":"David Semedo","orcid":null},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"David Semedo","raw_affiliation_strings":["NOVA LINCS, Lisboa\nNOVA FCT, Lisboa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA LINCS, Lisboa\nNOVA FCT, Lisboa","institution_ids":["https://openalex.org/I83558840"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.35660019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"8403","last_page":"8411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9466999769210815,"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":0.9466999769210815,"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":0.02590000070631504,"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":0.004900000058114529,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8108000159263611},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6970999836921692},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5900999903678894},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5544999837875366},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49410000443458557},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.44830000400543213},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44440001249313354},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.4106999933719635}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8108000159263611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692999839782715},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6970999836921692},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5900999903678894},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5264000296592712},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3046000003814697},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2646999955177307}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i10.37790","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37790","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37790","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37790","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37790","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6961545944213867,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"Anomaly":[1],"Understanding":[2],"(VAU)":[3],"is":[4],"a":[5,85,107,136,159,165,190],"novel":[6],"task":[7],"focused":[8],"on":[9,29,57,205,227],"describing":[10],"unusual":[11],"occurrences":[12],"in":[13,66,121,149,198,210],"videos.":[14,102],"Despite":[15],"growing":[16],"interest,":[17],"the":[18,43,54,92,111,143],"evaluation":[19,139,183],"of":[20,50,100,113,119,145,196],"VAU":[21,89,105],"remains":[22],"an":[23],"open":[24],"challenge.":[25],"Existing":[26],"benchmarks":[27],"rely":[28],"n-gram-based":[30],"metrics":[31],"(e.g.,":[32],"BLEU,":[33],"ROUGE-L)":[34],"or":[35],"LLM-based":[36],"evaluation.":[37],"The":[38],"first":[39],"fails":[40],"to":[41,200,213],"capture":[42],"rich,":[44,95],"free-form,":[45],"and":[46,97,128,156,167,220,232],"visually":[47],"grounded":[48],"nature":[49],"LVLM":[51,150],"responses,":[52],"while":[53],"latter":[55],"focuses":[56],"assessing":[58],"language":[59],"quality":[60],"over":[61],"factual":[62],"relevance,":[63],"often":[64],"resulting":[65],"subjective":[67],"judgments":[68],"that":[69,90,141,171,185,217],"are":[70],"misaligned":[71],"with":[72,110,176,193,234],"human":[73,174,194],"perception.":[74],"In":[75],"this":[76,80],"work,":[77],"we":[78],"address":[79],"issue":[81],"by":[82],"proposing":[83],"FineVAU,":[84],"new":[86],"benchmark":[87,132],"for":[88],"shifts":[91],"focus":[93],"towards":[94],"fine-grained":[96,154,179,221],"domain-specific":[98],"understanding":[99,115],"anomalous":[101,215],"We":[103],"formulate":[104],"as":[106],"three-fold":[108],"problem,":[109],"goal":[112],"comprehensively":[114],"key":[116],"descriptive":[117],"elements":[118,148],"anomalies":[120,197],"video:":[122],"events":[123,216,233],"(What),":[124],"participating":[125],"entities":[126],"(Who)":[127],"location":[129],"(Where).":[130],"Our":[131],"introduces":[133],"a)":[134],"FV-Score,":[135],"novel,":[137,160],"human-aligned":[138],"metric":[140,188],"assesses":[142],"presence":[144],"critical":[146,208],"visual":[147,180,236],"answers,":[151],"providing":[152],"interpretable,":[153],"feedback;":[155],"b)":[157],"FineW\u00b3,":[158],"comprehensive":[161],"dataset":[162],"curated":[163],"through":[164],"structured":[166],"fully":[168],"automatic":[169],"procedure":[170],"augments":[172],"existing":[173],"annotations":[175],"high":[177],"quality,":[178],"information.":[181],"Human":[182],"reveals":[184],"our":[186],"proposed":[187],"has":[189],"superior":[191],"alignment":[192],"perception":[195],"comparison":[199],"current":[201],"approaches.":[202],"Detailed":[203],"experiments":[204],"FineVAU":[206],"unveil":[207],"limitations":[209],"LVLM's":[211],"ability":[212],"perceive":[214],"require":[218],"spatial":[219],"temporal":[222],"understanding,":[223],"despite":[224],"strong":[225,235],"performance":[226],"coarse":[228],"grain,":[229],"static":[230],"information,":[231],"cues.":[237]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-27T00:00:00"}