{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:54:01Z","timestamp":1785912841045,"version":"3.56.0"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","award":["24YJA880097"],"award-info":[{"award-number":["24YJA880097"]}],"id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cviu.2026.104850","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:59:26Z","timestamp":1781798366000},"page":"104850","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Saliency-guided difference enhancement model for video anomaly detection"],"prefix":"10.1016","volume":"270","author":[{"given":"Qing","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongmei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104850_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2020.103915","article-title":"Anomaly detection in surveillance video based on bidirectional prediction","volume":"98","author":"Chen","year":"2020","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.cviu.2026.104850_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103263","article-title":"Guided image generation for improved surgical image segmentation","volume":"97","author":"Colleoni","year":"2024","journal-title":"Med. Image Anal."},{"issue":"12","key":"10.1016\/j.cviu.2026.104850_b3","doi-asserted-by":"crossref","first-page":"1848","DOI":"10.3390\/math12121848","article-title":"Masked feature compression for object detection","volume":"12","author":"Dai","year":"2024","journal-title":"Mathematics"},{"key":"10.1016\/j.cviu.2026.104850_b4","doi-asserted-by":"crossref","first-page":"1939","DOI":"10.7717\/peerj-cs.1939","article-title":"Improving smart home surveillance through YOLO model with transfer learning and quantization for enhanced accuracy and efficiency","volume":"10","author":"Dalal","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"10.1016\/j.cviu.2026.104850_b5","first-page":"1","article-title":"Generate anomalies from normal: a partial pseudo-anomaly augmented approach for video anomaly detection","author":"Dang","year":"2024","journal-title":"Vis. Comput."},{"issue":"1","key":"10.1016\/j.cviu.2026.104850_b6","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s11760-020-01740-1","article-title":"Residual spatiotemporal autoencoder for unsupervised video anomaly detection","volume":"15","author":"Deepak","year":"2020","journal-title":"Signal Image Video Process."},{"issue":"1","key":"10.1016\/j.cviu.2026.104850_b7","first-page":"1","article-title":"Positive and unlabeled learning on generating strategy for weakly anomaly detection","volume":"19","author":"Deng","year":"2025","journal-title":"Signal, Image Video Process."},{"key":"10.1016\/j.cviu.2026.104850_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.107115","article-title":"SSIM over MSE: A new perspective for video anomaly detection","volume":"185","author":"Fan","year":"2025","journal-title":"Neural Netw."},{"issue":"4","key":"10.1016\/j.cviu.2026.104850_b9","first-page":"989","article-title":"Anomaly detection algorithm based on deep learning and Gaussian mixture model","volume":"52","author":"Fan","year":"2024","journal-title":"Comput. Digit. Eng."},{"key":"10.1016\/j.cviu.2026.104850_b10","first-page":"4106","article-title":"Multi-encoder towards effective anomaly detection in videos","author":"Fang","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cviu.2026.104850_b11","doi-asserted-by":"crossref","unstructured":"Fischer, P., Dosovitskiy, A., Ilg, E., et al., 2015. FlowNet: Learning Optical Flow with Convolutional Networks. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 2758\u20132766.","DOI":"10.1109\/ICCV.2015.316"},{"key":"10.1016\/j.cviu.2026.104850_b12","doi-asserted-by":"crossref","unstructured":"Gong, D., Liu, L., et al., 2019. Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In: IEEE Conference on Computer Vision and Pattern Recognition. pp. 1705\u20131714.","DOI":"10.1109\/ICCV.2019.00179"},{"key":"10.1016\/j.cviu.2026.104850_b13","doi-asserted-by":"crossref","unstructured":"Hasan, M., Choi, J., Neumann, J., et al., 2016. Learning Temporal Regularity in Video Sequences. In: IEEE Conference on Computer Vision and Pattern Recognition. pp. 733\u2013742.","DOI":"10.1109\/CVPR.2016.86"},{"key":"10.1016\/j.cviu.2026.104850_b14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., et al., 2017. Mask R-CNN. In: IEEE Conference on Computer Vision. pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"issue":"7","key":"10.1016\/j.cviu.2026.104850_b15","doi-asserted-by":"crossref","first-page":"1885","DOI":"10.1007\/s11760-022-02148-9","article-title":"Video anomaly detection based on 3D convolutional auto-encoder","volume":"16","author":"Hu","year":"2022","journal-title":"Signal Image Video Process."},{"key":"10.1016\/j.cviu.2026.104850_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124846","article-title":"TDS-net: Transformer enhanced dual-stream network for video anomaly detection","volume":"256","author":"Hussain","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.cviu.2026.104850_b17","doi-asserted-by":"crossref","unstructured":"Jiang, H., Wei, W., Yuan, D., et al., 2024. Research on Anomaly Detection with Hierarchical Aggregation of Domain Context Integration. In: Proceedings of the 2024 3rd International Conference on Networks, Communications and Information Technology. pp. 81\u201386.","DOI":"10.1145\/3672121.3672137"},{"key":"10.1016\/j.cviu.2026.104850_b18","first-page":"3","article-title":"Video anomaly detection using encoder-decoder networks with video vision transformer and channel attention blocks","author":"Kobayashi","year":"2023"},{"key":"10.1016\/j.cviu.2026.104850_b19","first-page":"203","article-title":"Spatial-temporal cascade autoencoder for video anomaly detection in crowded scenes","volume":"vol. 20","author":"Li","year":"2023"},{"key":"10.1016\/j.cviu.2026.104850_b20","first-page":"1","article-title":"A novel spatio-temporal memory network for video anomaly detection","author":"Li","year":"2025","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.cviu.2026.104850_b21","article-title":"Adversarial composite prediction of normal video dynamics for anomaly detection","volume":"232","author":"Li","year":"2023","journal-title":"Int. Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104850_b22","doi-asserted-by":"crossref","unstructured":"Liu, W., Luo, W., Lian, D., Gao, S., 2018. Future frame prediction for anomaly detection\u2013a new baseline. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6536\u20136545.","DOI":"10.1109\/CVPR.2018.00684"},{"key":"10.1016\/j.cviu.2026.104850_b23","doi-asserted-by":"crossref","unstructured":"Lu, C., Shi, J., Jia, J., 2013. Abnormal event detection at 150 fps in matlab. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2720\u20132727.","DOI":"10.1109\/ICCV.2013.338"},{"key":"10.1016\/j.cviu.2026.104850_b24","first-page":"8984","article-title":"Crowd-level abnormal behavior detection via multi-scale motion consistency learning","volume":"vol. 37","author":"Luo","year":"2023"},{"issue":"3","key":"10.1016\/j.cviu.2026.104850_b25","doi-asserted-by":"crossref","first-page":"1070","DOI":"10.1109\/TPAMI.2019.2944377","article-title":"Video anomaly detection with sparse coding inspired deep neural networks","volume":"43","author":"Luo","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104850_b26","first-page":"1975","article-title":"Anomaly detection in crowded scenes(conference paper)","author":"Mahadevan","year":"2010","journal-title":"Proc. the IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.cviu.2026.104850_b27","doi-asserted-by":"crossref","unstructured":"Park, C., Cho, M.A., Lee, M., et al., 2022. FastAno: Fast anomaly detection via spatio-temporal patch transformation. In: IEEE Winter Conference on Applications of Computer Vision. pp. 2249\u20132259.","DOI":"10.1109\/WACV51458.2022.00197"},{"issue":"6","key":"10.1016\/j.cviu.2026.104850_b28","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1109\/TSMCC.2011.2178594","article-title":"Video-based abnormal human behavior recognition\u2014A review","volume":"42","author":"Popoola","year":"2012","journal-title":"IEEE Trans. Syst. Man & Cybern. Part C"},{"key":"10.1016\/j.cviu.2026.104850_b29","doi-asserted-by":"crossref","first-page":"2188","DOI":"10.1109\/LSP.2020.2976170","article-title":"Corrections to \u201dthree-stream network with bidirectional self-attention for action recognition in extreme low resolution videos\u201d","volume":"27","author":"Purwanto","year":"2020","journal-title":"Signal Process. Lett."},{"key":"10.1016\/j.cviu.2026.104850_b30","article-title":"Video anomaly detection using transformers and ensemble of convolutional auto-encoders","volume":"109","author":"Rahimpour","year":"2024","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.cviu.2026.104850_b31","doi-asserted-by":"crossref","unstructured":"Ristea, N.-C., Croitoru, F.-A., Ionescu, R.T., Popescu, M., Khan, F.S., Shah, M., et al., 2024. Self-distilled masked auto-encoders are efficient video anomaly detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15984\u201315995.","DOI":"10.1109\/CVPR52733.2024.01513"},{"issue":"1","key":"10.1016\/j.cviu.2026.104850_b32","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.vrih.2022.06.001","article-title":"COVAD: Content-oriented video anomaly detection using a self attention-based deep learning model","volume":"5","author":"Shao","year":"2023","journal-title":"Virtual Real. Intell. Hardw."},{"key":"10.1016\/j.cviu.2026.104850_b33","doi-asserted-by":"crossref","unstructured":"Sultani, W., Chen, C., Shah, M., 2018. Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6479\u20136488.","DOI":"10.1109\/CVPR.2018.00678"},{"key":"10.1016\/j.cviu.2026.104850_b34","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/j.patrec.2019.11.024","article-title":"Integrating prediction and reconstruction for anomaly detection","volume":"129","author":"Tang","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.cviu.2026.104850_b35","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.cviu.2026.104850_b36","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"issue":"6","key":"10.1016\/j.cviu.2026.104850_b37","doi-asserted-by":"crossref","first-page":"2301","DOI":"10.1109\/TNNLS.2021.3083152","article-title":"Robust unsupervised video anomaly detection by multipath frame prediction","volume":"33","author":"Wang","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"11","key":"10.1016\/j.cviu.2026.104850_b38","doi-asserted-by":"crossref","first-page":"7612","DOI":"10.1007\/s11263-025-02513-4","article-title":"Feature hallucination for self-supervised action recognition: L. Wang, p. Koniusz","volume":"133","author":"Wang","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cviu.2026.104850_b39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Qin, C., Bai, Y., et al., 2022. Making reconstruction-based method great again for video anomaly detection. In: IEEE Conference on Data Mining. pp. 1215\u20131220.","DOI":"10.1109\/ICDM54844.2022.00157"},{"issue":"12","key":"10.1016\/j.cviu.2026.104850_b40","first-page":"154","article-title":"Video abnormal event detection based on SE-u-net predictive network","volume":"41","author":"Wang","year":"2024","journal-title":"Comput. Appl. Softw."},{"issue":"3","key":"10.1016\/j.cviu.2026.104850_b41","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1049\/ipr2.12666","article-title":"Video abnormal behaviour detection based on pseudo-3D encoder and multi-cascade memory mechanism","volume":"17","author":"Wen","year":"2022","journal-title":"IET Image Process."},{"issue":"9","key":"10.1016\/j.cviu.2026.104850_b42","first-page":"4362","article-title":"Probabilistic memory auto-encoding network for abnormal behavior detection in surveillance videos","volume":"34","author":"Xiao","year":"2023","journal-title":"J. Softw."},{"issue":"8","key":"10.1016\/j.cviu.2026.104850_b43","doi-asserted-by":"crossref","first-page":"2121","DOI":"10.1007\/s11760-022-02174-7","article-title":"Motion-aware future frame prediction for video anomaly detection based on saliency perception","volume":"16","author":"Xu","year":"2022","journal-title":"Signal, Image Video Process."},{"key":"10.1016\/j.cviu.2026.104850_b44","doi-asserted-by":"crossref","unstructured":"Yin, H., Yang, C., Lu, J., 2022. Research on remote sensing image classification algorithm based on EfficientNet. In: International Conference on Intelligent Computing and Signal Processing. pp. 1757\u20131761.","DOI":"10.1109\/ICSP54964.2022.9778437"},{"issue":"2","key":"10.1016\/j.cviu.2026.104850_b45","first-page":"69","article-title":"Autoencoder video human abnormal behavior detection model combined with attention mechanism","volume":"44","author":"Zhang","year":"2023","journal-title":"Laser J."},{"issue":"01","key":"10.1016\/j.cviu.2026.104850_b46","first-page":"14","article-title":"Overview of video based human abnormal behavior recognition and detection methods","volume":"37","author":"Zhang","year":"2022","journal-title":"Control Decis."},{"key":"10.1016\/j.cviu.2026.104850_b47","first-page":"1","article-title":"Bidirectional prediction bip-GAN pedestrian video anomaly event automatic detection","author":"Zhang","year":"2025","journal-title":"Geomatics Inf. Sci. Wuhan Univ."},{"key":"10.1016\/j.cviu.2026.104850_b48","first-page":"10761","article-title":"Video anomaly detection with motion and appearance guided patch diffusion model","volume":"vol. 39","author":"Zhou","year":"2025"},{"key":"10.1016\/j.cviu.2026.104850_b49","article-title":"Anomaly detection using invariant rules in industrial control systems","volume":"154","author":"Zhu","year":"2022","journal-title":"Control Eng. Pract."},{"key":"10.1016\/j.cviu.2026.104850_b50","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."}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002171?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002171?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:38:17Z","timestamp":1785911897000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226002171"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":50,"alternative-id":["S1077314226002171"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104850","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Saliency-guided difference enhancement model for video anomaly detection","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104850","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104850"}}