{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:00:52Z","timestamp":1776441652270,"version":"3.51.2"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["CUC25SG012"],"award-info":[{"award-number":["CUC25SG012"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["CUC25SG008"],"award-info":[{"award-number":["CUC25SG008"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3630089","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:56:20Z","timestamp":1762455380000},"page":"4359-4363","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Video Anomaly Understanding via Multi-Task Instruction Tuning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8096-7243","authenticated-orcid":false,"given":"Xuxu","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3481-7820","authenticated-orcid":false,"given":"Xiaoyu","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0917-001X","authenticated-orcid":false,"given":"Zihao","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20876-9_31"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01246"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3356910"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3555544"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3324299"},{"key":"ref7","article-title":"Deep learning for video anomaly detection: A review","author":"Wu","year":"2024"},{"key":"ref8","article-title":"Video anomaly detection and explanation via large language models","author":"Lv","year":"2024"},{"key":"ref9","article-title":"Holmes-VAD: Towards unbiased and explainable video anomaly detection via multi-modal LLM","author":"Zhang","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01292"},{"key":"ref11","first-page":"95666","article-title":"SafeWatch: An efficient safety-policy following video guardrail model with transparent explanations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2025"},{"key":"ref12","first-page":"139751","article-title":"Hawk: Learning to understand open-world video anomalies","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tang","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref15","first-page":"89943","article-title":"Advancing video anomaly detection: A concise review and a new dataset","volume-title":"Proc. 38th Int. Conf. Neural Inf. Process. Syst.","author":"Zhu","year":"2024"},{"key":"ref16","article-title":"When, where, and what? A new dataset for anomaly detection in driving videos","author":"Yao","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072863"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12258"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3230262"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02082"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3414263"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01778"},{"key":"ref25","article-title":"Language-guided open-world video anomaly detection under weak supervision","author":"Liu","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref28","article-title":"ActionClip: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref30","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025"},{"key":"ref31","article-title":"VideoLLama 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025"},{"key":"ref32","article-title":"AssistPDA: An online video surveillance assistant for video anomaly prediction, detection, and analysis","author":"Yang","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1053"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.131"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/11230620.pdf?arnumber=11230620","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:43:15Z","timestamp":1763790195000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230620\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3630089","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}