{"id":"https://openalex.org/W4415971125","doi":"https://doi.org/10.1109/lsp.2025.3630089","title":"Enhancing Video Anomaly Understanding via Multi-Task Instruction Tuning","display_name":"Enhancing Video Anomaly Understanding via Multi-Task Instruction Tuning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415971125","doi":"https://doi.org/10.1109/lsp.2025.3630089"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2025.3630089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3630089","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xuxu Wang","orcid":"https://orcid.org/0009-0000-8096-7243"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuxu Wang","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357651","display_name":"Xiaoyu Wu","orcid":"https://orcid.org/0000-0003-3481-7820"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Wu","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037194804","display_name":"Zihao Liu","orcid":"https://orcid.org/0000-0002-0917-001X"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Liu","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17036764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"4359","last_page":"4363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.975600004196167,"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":0.975600004196167,"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":0.008899999782443047,"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":0.0019000000320374966,"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":0.6984000205993652},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6409000158309937},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6061000227928162},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5299999713897705},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5081999897956848},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4862000048160553},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.412200003862381},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3840999901294708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177000284194946},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6984000205993652},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6409000158309937},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6061000227928162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5809000134468079},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3345000147819519},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2676999866962433},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3630089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3630089","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2105792905","display_name":null,"funder_award_id":"CUC25SG008","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7775931665","display_name":null,"funder_award_id":"CUC25SG012","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2163612318","https://openalex.org/W2963215781","https://openalex.org/W2963610939","https://openalex.org/W2963795951","https://openalex.org/W2970785793","https://openalex.org/W3035252911","https://openalex.org/W3058842179","https://openalex.org/W3089682612","https://openalex.org/W3164956984","https://openalex.org/W4319996369","https://openalex.org/W4385572754","https://openalex.org/W4386065554","https://openalex.org/W4387587791","https://openalex.org/W4390873154","https://openalex.org/W4391096953","https://openalex.org/W4393153999","https://openalex.org/W4400229237","https://openalex.org/W4402704561","https://openalex.org/W4402775263","https://openalex.org/W4404784276","https://openalex.org/W4409014683","https://openalex.org/W4413157891"],"related_works":[],"abstract_inverted_index":{"Video":[0,6],"Anomaly":[1,7],"Understanding":[2],"(VAU)":[3],"extends":[4],"traditional":[5],"Detection":[8],"by":[9],"enabling":[10],"both":[11],"identification":[12],"and":[13,35,53,66,85,99],"interpretation":[14],"of":[15,46,63,106],"abnormal":[16,83],"events":[17],"via":[18],"natural":[19],"language.":[20],"Building":[21],"on":[22,91,97],"instruction-tuned":[23],"multimodal":[24],"large":[25],"language":[26],"models":[27],"(MLLMs),":[28],"we":[29],"present":[30],"a":[31,43],"unified":[32],"VAU":[33],"framework":[34],"perform":[36],"multi-task":[37,108],"LoRA":[38],"fine-tuning.":[39],"We":[40],"construct":[41],"PreVAD-Instruct27k,":[42,92],"large-scale":[44],"dataset":[45],"27,854":[47],"videos":[48],"annotated":[49],"with":[50],"categories,":[51],"descriptions,":[52],"open-ended":[54],"question":[55],"answering":[56],"(QA)":[57],"pairs.":[58],"PreVAD-Instruct27k":[59],"enables":[60],"joint":[61],"optimization":[62],"classification,":[64],"description,":[65,84],"QA":[67,90],"tasks.":[68],"Under":[69],"sparse":[70],"frame":[71],"sampling,":[72],"our":[73],"model":[74],"achieves":[75],"77.72%":[76],"classification":[77],"accuracy,":[78],"93.62%":[79],"UniEval":[80,87],"score":[81,88],"for":[82,89],"90.64%":[86],"while":[93],"maintaining":[94],"strong":[95],"generalization":[96],"XD-Violence":[98],"UCF-Crime.":[100],"Ablation":[101],"studies":[102],"confirm":[103],"the":[104,107],"effectiveness":[105],"design.":[109]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-06T00:00:00"}