{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:05:47Z","timestamp":1783919147836,"version":"3.55.0"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF0717402"],"award-info":[{"award-number":["2023YFF0717402"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.ins.2026.123589","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T21:55:50Z","timestamp":1777931750000},"page":"123589","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["RAG4VAD: A training-free retrieval-augmented generation framework for explainable video anomaly detection"],"prefix":"10.1016","volume":"753","author":[{"given":"Qiyue","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxia","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongjun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2026.123589_bib0005","doi-asserted-by":"crossref","first-page":"89943","DOI":"10.52202\/079017-2856","article-title":"Advancing video anomaly detection: a concise review and a new dataset","volume":"37","author":"Zhu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123589_bib0010","first-page":"1","article-title":"Video anomaly detection in 10 years: a survey and outlook","author":"Abdalla","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.ins.2026.123589_bib0015","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"13588","article-title":"A hybrid video anomaly detection framework via memory-augmented flow reconstruction and flow-guided frame prediction","author":"Liu","year":"2021"},{"key":"10.1016\/j.ins.2026.123589_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107830","article-title":"Attention-guided generator with dual discriminator GAN for real-time video anomaly detection","volume":"131","author":"Singh","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.ins.2026.123589_bib0025","article-title":"Cf2m-net: cross-feature fusion and memory-constraint network for video anomaly detection","author":"Ma","year":"2025","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2026.123589_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"24185","article-title":"Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2024"},{"key":"10.1016\/j.ins.2026.123589_bib0035","author":"Guo"},{"key":"10.1016\/j.ins.2026.123589_bib0040","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123589_bib0045","series-title":"British Machine Vision Conference","article-title":"Learning not to reconstruct anomalies","author":"Astrid","year":"2021"},{"key":"10.1016\/j.ins.2026.123589_bib0050","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20392","article-title":"A new comprehensive benchmark for semi-supervised video anomaly detection and anticipation","author":"Cao","year":"2023"},{"key":"10.1016\/j.ins.2026.123589_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2022.103615","article-title":"Unsupervised video anomaly detection based on multi-timescale trajectory prediction","volume":"227","author":"Sun","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.ins.2026.123589_bib0060","series-title":"Proceedings of the 27th ACM International Conference on Multimedia","first-page":"1805","article-title":"Anopcn: video anomaly detection via deep predictive coding network","author":"Ye","year":"2019"},{"key":"10.1016\/j.ins.2026.123589_bib0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105644","article-title":"MG-KG: unsupervised video anomaly detection based on motion guidance and knowledge graph","volume":"162","author":"Sun","year":"2025","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.ins.2026.123589_bib0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130348","article-title":"A hyperparameter-free Scene-Motion aware cross attention network for video anomaly detection in surveillance","author":"Sun","year":"2025","journal-title":"Neurocomputing"},{"issue":"9","key":"10.1016\/j.ins.2026.123589_bib0075","doi-asserted-by":"crossref","first-page":"8398","DOI":"10.1109\/TCSVT.2024.3382633","article-title":"VADiffusion: compressed domain information guided conditional diffusion for video anomaly detection","volume":"34","author":"Liu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"10.1016\/j.ins.2026.123589_bib0080","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3439950","article-title":"Deep learning for anomaly detection: a review","volume":"54","author":"Pang","year":"2021","journal-title":"ACM comput. surv. (CSUR)"},{"key":"10.1016\/j.ins.2026.123589_bib0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105139","article-title":"M2vad: multiview multimodality transformer-based weakly supervised video anomaly detection","volume":"149","author":"Paulraj","year":"2024","journal-title":"Image Vis. Comput."},{"issue":"5","key":"10.1016\/j.ins.2026.123589_bib0090","first-page":"2293","article-title":"A survey of single-scene video anomaly detection","volume":"44","author":"Ramachandra","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.ins.2026.123589_bib0095","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10318","article-title":"Multimodal motion conditioned diffusion model for skeleton-based video anomaly detection","author":"Flaborea","year":"2023"},{"key":"10.1016\/j.ins.2026.123589_bib0100","article-title":"One model connects all graphs: towards training one unified model for multi-domain graph pre-training using adaptive vector quantization","author":"Xie","year":"2025","journal-title":"Inf. Fusion"},{"issue":"2","key":"10.1016\/j.ins.2026.123589_bib0105","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104460","article-title":"Text-free inductive knowledge graph embedding via meta graph-based prompt learning","volume":"63","author":"Yi","year":"2026","journal-title":"Inf. Process. Manag."},{"key":"10.1016\/j.ins.2026.123589_bib0110","series-title":"European Conference on Computer Vision","first-page":"304","article-title":"Follow the rules: reasoning for video anomaly detection with large language models","author":"Yang","year":"2024"},{"key":"10.1016\/j.ins.2026.123589_bib0115","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18527","article-title":"Harnessing large language models for training-free video anomaly detection","author":"Zanella","year":"2024"},{"key":"10.1016\/j.ins.2026.123589_bib0120","doi-asserted-by":"crossref","first-page":"139751","DOI":"10.52202\/079017-4435","article-title":"Hawk: learning to understand open-world video anomalies","volume":"37","author":"Tang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123589_bib0125","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.ins.2026.123589_bib0130","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.ins.2026.123589_bib0135","author":"Bai"},{"key":"10.1016\/j.ins.2026.123589_bib0140","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2720","article-title":"Abnormal event detection at 150 fps in matlab","author":"Lu","year":"2013"},{"key":"10.1016\/j.ins.2026.123589_bib0145","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"341","article-title":"A revisit of sparse coding based anomaly detection in stacked RNN framework","author":"Luo","year":"2017"},{"key":"10.1016\/j.ins.2026.123589_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6154","article-title":"Cascade r-cnn: delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.1016\/j.ins.2026.123589_bib0155","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.ins.2026.123589_bib0160","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2462","article-title":"Flownet 2.0: evolution of optical flow estimation with deep networks","author":"Ilg","year":"2017"},{"key":"10.1016\/j.ins.2026.123589_bib0165","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14372","article-title":"Learning memory-guided normality for anomaly detection","author":"Park","year":"2020"},{"key":"10.1016\/j.ins.2026.123589_bib0170","doi-asserted-by":"crossref","first-page":"1810","DOI":"10.1109\/TIP.2024.3372466","article-title":"Context recovery and knowledge retrieval: a novel two-stream framework for video anomaly detection","volume":"33","author":"Cao","year":"2024","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"10.1016\/j.ins.2026.123589_bib0175","doi-asserted-by":"crossref","first-page":"1519","DOI":"10.1109\/TCSVT.2023.3297114","article-title":"Learning Appearance-Motion synergy via memory-guided event prediction for video anomaly detection","volume":"34","author":"Guo","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"11","key":"10.1016\/j.ins.2026.123589_bib0180","doi-asserted-by":"crossref","first-page":"9389","DOI":"10.1109\/TNNLS.2022.3159538","article-title":"Self-supervised attentive generative adversarial networks for video anomaly detection","volume":"34","author":"Huang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.ins.2026.123589_bib0185","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14592","article-title":"Video event restoration based on keyframes for video anomaly detection","author":"Yang","year":"2023"},{"key":"10.1016\/j.ins.2026.123589_bib0190","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"5527","article-title":"Feature prediction diffusion model for video anomaly detection","author":"Yan","year":"2023"},{"key":"10.1016\/j.ins.2026.123589_bib0195","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111759","article-title":"Unsupervised video anomaly detection by memory network with autoencoders in Euclidean and non-euclidean spaces","author":"Kim","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.ins.2026.123589_bib0200","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111595","article-title":"MPE: multi-frame prediction error-based video anomaly detection framework for robust anomaly inference","volume":"164","author":"Kim","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.ins.2026.123589_bib0205","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7842","article-title":"Object-centric auto-encoders and dummy anomalies for abnormal event detection in video","author":"Ionescu","year":"2019"},{"key":"10.1016\/j.ins.2026.123589_bib0210","series-title":"Proceedings of the 28th ACM International Conference on Multimedia","first-page":"583","article-title":"Cloze test helps: effective video anomaly detection via learning to complete video events","author":"Yu","year":"2020"},{"key":"10.1016\/j.ins.2026.123589_bib0215","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"307","article-title":"Hierarchical graph embedded pose regularity learning via spatio-temporal transformer for abnormal behavior detection","author":"Huang","year":"2022"},{"key":"10.1016\/j.ins.2026.123589_bib0220","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10330","article-title":"Video anomaly detection via sequentially learning multiple pretext tasks","author":"Shi","year":"2023"},{"key":"10.1016\/j.ins.2026.123589_bib0225","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/j.patrec.2024.08.013","article-title":"An unsupervised video anomaly detection method via optical flow decomposition and Spatio-Temporal feature learning","volume":"185","author":"Fan","year":"2024","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.ins.2026.123589_bib0230","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111021","article-title":"Video anomaly detection via self-supervised and spatio-temporal proxy tasks learning","volume":"158","author":"Yang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.ins.2026.123589_bib0235","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3313","article-title":"Online detection of unusual events in videos via dynamic sparse coding","author":"Zhao","year":"2011"},{"key":"10.1016\/j.ins.2026.123589_bib0240","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2895","article-title":"Unmasking the abnormal events in video","author":"Tudor Ionescu","year":"2017"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526005207?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526005207?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T04:48:48Z","timestamp":1783918128000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025526005207"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":48,"alternative-id":["S0020025526005207"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123589","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RAG4VAD: A training-free retrieval-augmented generation framework for explainable video anomaly detection","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123589","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"123589"}}