{"id":"https://openalex.org/W7127095703","doi":"https://doi.org/10.1016/j.knosys.2026.115466","title":"Hierarchical vision-language model with comprehensive language description for video anomaly detection","display_name":"Hierarchical vision-language model with comprehensive language description for video anomaly detection","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7127095703","doi":"https://doi.org/10.1016/j.knosys.2026.115466"},"language":"en","primary_location":{"id":"doi:10.1016/j.knosys.2026.115466","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115466","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.knosys.2026.115466","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124807617","display_name":"Muaz Al Radi","orcid":null},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Muaz Al Radi","raw_affiliation_strings":["Khalifa University of Science Technology, UAE"],"raw_orcid":"https://orcid.org/0000-0002-4309-1585","affiliations":[{"raw_affiliation_string":"Khalifa University of Science Technology, UAE","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120955623","display_name":"Sajid Javed","orcid":null},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Sajid Javed","raw_affiliation_strings":["Khalifa University of Science Technology, UAE"],"raw_orcid":"https://orcid.org/0000-0002-0036-2875","affiliations":[{"raw_affiliation_string":"Khalifa University of Science Technology, UAE","institution_ids":["https://openalex.org/I176601375"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5124807617"],"corresponding_institution_ids":["https://openalex.org/I176601375"],"apc_list":{"value":3130,"currency":"USD","value_usd":3130},"apc_paid":{"value":3130,"currency":"USD","value_usd":3130},"fwci":28.3402,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9860003,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"337","issue":null,"first_page":"115466","last_page":"115466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9739999771118164,"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":0.9739999771118164,"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":0.0066999997943639755,"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":0.002899999963119626,"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":0.6044999957084656},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5778999924659729},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.539900004863739},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5230000019073486},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5033000111579895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5015000104904175},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4560999870300293},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.4374000132083893},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4269999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331000208854675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593999862670898},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6044999957084656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.539900004863739},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5230000019073486},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4269999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3937999904155731},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3375999927520752},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3043999969959259},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.knosys.2026.115466","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115466","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.knosys.2026.115466","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115466","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.649807870388031,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1689711448","https://openalex.org/W1970088130","https://openalex.org/W2081580037","https://openalex.org/W2097511040","https://openalex.org/W2132870739","https://openalex.org/W2913427224","https://openalex.org/W2915683453","https://openalex.org/W2964032056","https://openalex.org/W2972156365","https://openalex.org/W2981638912","https://openalex.org/W3044374951","https://openalex.org/W3080722105","https://openalex.org/W3117272077","https://openalex.org/W3129071613","https://openalex.org/W3176923149","https://openalex.org/W3198377975","https://openalex.org/W4213019189","https://openalex.org/W4283727315","https://openalex.org/W4283811196","https://openalex.org/W4297371868","https://openalex.org/W4312889062","https://openalex.org/W4362475012","https://openalex.org/W4378228743","https://openalex.org/W4384436171","https://openalex.org/W4385496637","https://openalex.org/W4386790226","https://openalex.org/W4387789514","https://openalex.org/W4391614403","https://openalex.org/W4393970287","https://openalex.org/W4396669743","https://openalex.org/W4399268507","https://openalex.org/W4409387207","https://openalex.org/W4409507112","https://openalex.org/W4410856148","https://openalex.org/W4414447489"],"related_works":[],"abstract_inverted_index":{"\u2022":[0,10,20,30,42],"Proposed":[1,11],"a":[2,32,57,117,137,157,196],"hierarchical":[3,118,138,152,209],"VAD":[4,34,82,198,244],"model":[5,175,212],"capturing":[6,126],"multi-granularity":[7],"temporal":[8,102],"information.":[9],"learning":[12],"comprehensive":[13,160],"textual":[14,93,161],"descriptions":[15,162],"using":[16,165],"VLMs":[17,167],"and":[18,27,49,68,86,92,147,155,179,190,217,231],"LLMs.":[19],"Achieved":[21],"robust":[22,223],"detection":[23],"of":[24,39,132,140,163,238],"both":[25,214],"fine":[26],"coarse-grained":[28],"anomalies.":[29,110],"Introduced":[31],"training-free":[33,197],"framework":[35,199],"based":[36,200],"on":[37,46,170,201,228,250],"similarity":[38,202],"aligned":[40],"concepts.":[41],"Demonstrate":[43],"superior":[44,236],"performance":[45,237],"various":[47],"datasets":[48,233],"supervision":[50],"levels.":[51],"Video":[52],"Anomaly":[53],"Detection":[54],"(VAD)":[55],"is":[56,180,248],"crucial":[58],"task":[59],"in":[60,65,73,83,186],"computer":[61],"vision,":[62],"with":[63],"applications":[64],"surveillance,":[66],"transportation,":[67],"industrial":[69],"monitoring.":[70],"Recent":[71],"advancements":[72],"Vision-Language":[74],"Models":[75],"(VLMs)":[76],"have":[77],"shown":[78],"promising":[79],"direction":[80],"toward":[81],"weakly":[84,187],"supervised":[85],"unsupervised":[87],"settings":[88],"by":[89,125],"leveraging":[90],"visual":[91,153],"modalities.":[94],"However,":[95],"existing":[96,166],"VLM-based":[97],"methods":[98],"often":[99],"overlook":[100],"coarse-to-fine":[101],"information,":[103,220],"limiting":[104],"their":[105],"ability":[106],"to":[107,222,242],"handle":[108],"complex":[109,206],"To":[111],"address":[112],"this":[113],"issue,":[114],"we":[115],"propose":[116],"VLM":[119],"that":[120],"enhances":[121],"visual-textual":[122],"feature":[123,224],"representation":[124],"video":[127],"content":[128],"at":[129],"multiple":[130],"levels":[131],"abstraction.":[133],"Our":[134,174],"algorithm":[135],"generates":[136],"view":[139],"the":[141,235],"video,":[142],"dividing":[143],"it":[144],"into":[145],"short":[146],"long":[148],"views.":[149],"We":[150,193],"extract":[151],"features":[154],"construct":[156],"bag":[158],"containing":[159],"anomalies":[164],"without":[168],"relying":[169],"ground":[171],"truth":[172],"data.":[173],"fuses":[176],"these":[177],"modalities":[178],"fine-tuned":[181],"for":[182],"anomaly":[183],"score":[184],"prediction":[185],"supervised,":[188],"unsupervised,":[189],"one-class":[191],"settings.":[192],"also":[194],"introduce":[195],"scores.":[203],"By":[204],"aligning":[205],"concepts":[207],"across":[208],"views,":[210],"our":[211,239],"captures":[213],"fine-grained":[215],"details":[216],"high-level":[218],"contextual":[219],"leading":[221],"representations.":[225],"Extensive":[226],"experiments":[227],"UCF-Crime,":[229],"ShanghaiTech,":[230],"XD-Violence":[232],"demonstrate":[234],"method":[240],"compared":[241],"State-Of-The-Art":[243],"methods.":[245],"The":[246],"code":[247],"available":[249],"GitHub":[251],"at:":[252],"https://github.com/MR81224/HVLMCLD-VAD":[253],".":[254]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-12T08:28:47.272897","created_date":"2026-02-03T00:00:00"}