{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T13:21:12Z","timestamp":1788528072838,"version":"build-2803163510"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114314","type":"journal-article","created":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:39:57Z","timestamp":1783147197000},"page":"114314","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["MGFN++: Magnitude-contrastive glance-and-focus network for weakly-supervised video anomaly detection"],"prefix":"10.1016","volume":"180","author":[{"given":"Yingxian","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Bin","family":"Kou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wilton","family":"Fok","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengzhe","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yik-Chung","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114314_b1","doi-asserted-by":"crossref","unstructured":"J. Feng, F. Hong, W. Zheng, MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection, in: 2021 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2021.","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"10.1016\/j.patcog.2026.114314_b2","doi-asserted-by":"crossref","unstructured":"Y. Tian, G. Pang, Y. Chen, R. Singh, J.W. Verjans, G. Carneiro, Weakly-Supervised Video Anomaly Detection With Robust Temporal Feature Magnitude Learning, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2021, pp. 4975\u20134986.","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"10.1016\/j.patcog.2026.114314_b3","doi-asserted-by":"crossref","unstructured":"P. Wu, j. Liu, Y. Shi, Y. Sun, F. Shao, Z. Wu, Z. Yang, Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision, in: European Conference on Computer Vision, ECCV, 2020.","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"10.1016\/j.patcog.2026.114314_b4","doi-asserted-by":"crossref","first-page":"3513","DOI":"10.1109\/TIP.2021.3062192","article-title":"Learning causal temporal relation and feature discrimination for anomaly detection","volume":"30","author":"Wu","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114314_b5","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Nie, C. Long, Q. Zhang, G. Li, A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction, in: Proceedings of the IEEE International Conference on Computer Vision, 2021.","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"10.1016\/j.patcog.2026.114314_b6","doi-asserted-by":"crossref","unstructured":"H. Park, J. Noh, B. Ham, Learning Memory-guided Normality for Anomaly Detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 14372\u201314381.","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"10.1016\/j.patcog.2026.114314_b7","series-title":"Anomaly detection in video sequence with appearance-motion correspondence","author":"Nguyen","year":"2019"},{"key":"10.1016\/j.patcog.2026.114314_b8","unstructured":"M.Z. Zaheer, J.-H. Lee, M. Astrid, A. Mahmood, S.-I. Lee, Cleaning label noise with clusters for minimally supervised anomaly detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, June 2020."},{"key":"10.1016\/j.patcog.2026.114314_b9","series-title":"European Conference on Computer Vision","first-page":"358","article-title":"CLAWS: Clustering assisted weakly supervised learning with normalcy suppression for anomalous event detection","author":"Zaheer","year":"2020"},{"key":"10.1016\/j.patcog.2026.114314_b10","doi-asserted-by":"crossref","unstructured":"Y. Chen, Z. Liu, B. Zhang, W. Fok, X. Qi, Y.-C. Wu, MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection, in: AAAI2023, 2022.","DOI":"10.1609\/aaai.v37i1.25112"},{"key":"10.1016\/j.patcog.2026.114314_b11","doi-asserted-by":"crossref","unstructured":"W. Sultani, C. Chen, M. Shah, Real-World Anomaly Detection in Surveillance Videos, in: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2018.","DOI":"10.1109\/CVPR.2018.00678"},{"key":"10.1016\/j.patcog.2026.114314_b12","first-page":"1","article-title":"Deep learning for video anomaly detection: A review","author":"Wu","year":"2026","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114314_b13","series-title":"Anomaly locality in video surveillance","author":"Landi","year":"2019"},{"key":"10.1016\/j.patcog.2026.114314_b14","doi-asserted-by":"crossref","unstructured":"R.T. Ionescu, F.S. Khan, M. Georgescu, L. Shao, Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video, in: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2018.","DOI":"10.1109\/CVPR.2019.00803"},{"key":"10.1016\/j.patcog.2026.114314_b15","series-title":"Proceedings of the 25th ACM International Conference on Multimedia","first-page":"1933","article-title":"Spatio-temporal AutoEncoder for video anomaly detection","author":"Zhao","year":"2017"},{"issue":"2","key":"10.1016\/j.patcog.2026.114314_b16","first-page":"1395","article-title":"Self-training multi-sequence learning with transformer for weakly supervised video anomaly detection","volume":"36","author":"Li","year":"2022","journal-title":"Proc. the AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114314_b17","series-title":"Pattern Recognition and Computer Vision","first-page":"284","article-title":"Dual-scale temporal dependency learning for unsupervised video anomaly detection","author":"Li","year":"2025"},{"key":"10.1016\/j.patcog.2026.114314_b18","series-title":"Generative cooperative learning for unsupervised video anomaly detection","author":"Zaheer","year":"2022"},{"key":"10.1016\/j.patcog.2026.114314_b19","series-title":"BatchNorm-based weakly supervised video anomaly detection","author":"Zhou","year":"2023"},{"key":"10.1016\/j.patcog.2026.114314_b20","series-title":"Learning weakly supervised audio-visual violence detection in hyperbolic space","author":"Peng","year":"2024"},{"key":"10.1016\/j.patcog.2026.114314_b21","series-title":"Cross-modal fusion and attention mechanism for weakly supervised video anomaly detection","author":"Ghadiya","year":"2024"},{"key":"10.1016\/j.patcog.2026.114314_b22","first-page":"1","article-title":"Multimodal evidential learning for open-world weakly-supervised video anomaly detection","author":"Huang","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114314_b23","series-title":"Flashback: Memory-driven zero-shot, real-time video anomaly detection","author":"Lee","year":"2025"},{"key":"10.1016\/j.patcog.2026.114314_b24","doi-asserted-by":"crossref","unstructured":"Y. Chang, Z. Tu, W. Xie, J. Yuan, Clustering Driven Deep Autoencoder for Video Anomaly Detection, in: Computer Vision \u2013 ECCV 2020, 16th European Conference, 2022, pp. 329\u2013345.","DOI":"10.1007\/978-3-030-58555-6_20"},{"key":"10.1016\/j.patcog.2026.114314_b25","doi-asserted-by":"crossref","unstructured":"Y. Lu, F. Yu, M.K.K. Reddy, Y. Wang, Few-shot Scene-adaptive Anomaly Detection, in: European Conference on Computer Vision, 2020.","DOI":"10.1007\/978-3-030-58558-7_8"},{"key":"10.1016\/j.patcog.2026.114314_b26","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8022","article-title":"Unbiased multiple instance learning for weakly supervised video anomaly detection","author":"Lv","year":"2023"},{"key":"10.1016\/j.patcog.2026.114314_b27","doi-asserted-by":"crossref","unstructured":"J.-X. Zhong, N. Li, W. Kong, S. Liu, T.H. Li, G. Li, Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection, in: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2019.","DOI":"10.1109\/CVPR.2019.00133"},{"key":"10.1016\/j.patcog.2026.114314_b28","doi-asserted-by":"crossref","unstructured":"B. Ramachandra, M.J. Jones, R.R. Vatsavai, Learning a distance function with a Siamese network to localize anomalies in videos, in: 2020 IEEE Winter Conference on Applications of Computer Vision, WACV, 2020.","DOI":"10.1109\/WACV45572.2020.9093417"},{"key":"10.1016\/j.patcog.2026.114314_b29","doi-asserted-by":"crossref","unstructured":"B. Wan, Y. Fang, X. Xia, J. Mei, Weakly Supervised Video Anomaly Detection via Center-Guided Discriminative Learning, in: Proceedings of the IEEE International Conference on Multimedia and Expo, 2020.","DOI":"10.1109\/ICME46284.2020.9102722"},{"key":"10.1016\/j.patcog.2026.114314_b30","doi-asserted-by":"crossref","first-page":"5575","DOI":"10.1109\/TMM.2023.3336576","article-title":"Abnormal ratios guided multi-phase self-training for weakly-supervised video anomaly detection","volume":"26","author":"Shi","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114314_b31","series-title":"Mixture of experts guided by Gaussian splatters matters: A new approach to weakly-supervised video anomaly detection","author":"D\u2019Amicantonio","year":"2025"},{"key":"10.1016\/j.patcog.2026.114314_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110898","article-title":"Semantic-driven dual consistency learning for weakly supervised video anomaly detection","volume":"157","author":"Su","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114314_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111978","article-title":"VPE-WSVAD: Visual prompt exemplars for weakly-supervised video anomaly detection","volume":"299","author":"Su","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.patcog.2026.114314_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129576","article-title":"Spatio-temporal graph-based self-labeling for video anomaly detection","volume":"627","author":"Xing","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.114314_b35","series-title":"Advances in Neural Information Processing Systems","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.patcog.2026.114314_b36","series-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"10.1016\/j.patcog.2026.114314_b37","series-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.patcog.2026.114314_b38","series-title":"Pre-trained image processing transformer","author":"Chen","year":"2021"},{"key":"10.1016\/j.patcog.2026.114314_b39","doi-asserted-by":"crossref","unstructured":"N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, S. Zagoruyko, End-to-End Object Detection with Transformers, in: European Conference on Computer Vision, ECCV, 2020.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"10.1016\/j.patcog.2026.114314_b40","series-title":"Segmenter: Transformer for semantic segmentation","author":"Strudel","year":"2021"},{"key":"10.1016\/j.patcog.2026.114314_b41","doi-asserted-by":"crossref","unstructured":"R. Girdhar, J. Carreira, C. Doersch, A. Zisserman, Video Action Transformer Network, in: 2019 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2019.","DOI":"10.1109\/CVPR.2019.00033"},{"key":"10.1016\/j.patcog.2026.114314_b42","unstructured":"G. Bertasius, H. Wang, L. Torresani, Is Space-Time Attention All You Need for Video Understanding?, in: Proceedings of the International Conference on Machine Learning, ICML, 2021."},{"key":"10.1016\/j.patcog.2026.114314_b43","series-title":"RelationNet++: Bridging visual representations for object detection via transformer decoder","author":"Chi","year":"2020"},{"key":"10.1016\/j.patcog.2026.114314_b44","series-title":"LiDAR-based online 3D video object detection with graph-based message passing and spatiotemporal transformer attention","author":"Yin","year":"2020"},{"key":"10.1016\/j.patcog.2026.114314_b45","series-title":"2019 IEEE\/CVF International Conference on Computer Vision Workshop","first-page":"1553","article-title":"Video multitask transformer network","author":"Seong","year":"2019"},{"key":"10.1016\/j.patcog.2026.114314_b46","series-title":"Transformer-XL: Attentive language models beyond a fixed-length context","author":"Dai","year":"2019"},{"key":"10.1016\/j.patcog.2026.114314_b47","series-title":"Compressive transformers for long-range sequence modelling","author":"Rae","year":"2019"},{"key":"10.1016\/j.patcog.2026.114314_b48","series-title":"2019 IEEE International Conference on Image Processing","first-page":"4030","article-title":"Temporal convolutional network with complementary inner bag loss for weakly supervised anomaly detection","author":"Zhang","year":"2019"},{"issue":"4","key":"10.1016\/j.patcog.2026.114314_b49","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1109\/TCDS.2024.3349705","article-title":"Multiple instance learning for cheating detection and localization in online examinations","volume":"16","author":"Liu","year":"2024","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"10.1016\/j.patcog.2026.114314_b50","doi-asserted-by":"crossref","first-page":"4505","DOI":"10.1109\/TIP.2021.3072863","article-title":"Localizing anomalies from weakly-labeled videos","volume":"30","author":"Lv","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114314_b51","series-title":"Advances in Neural Informa- Tion Processing Systems","first-page":"8024","article-title":"Automatic differentiation in pytorch","author":"Paszke","year":"2019"},{"key":"10.1016\/j.patcog.2026.114314_b52","doi-asserted-by":"crossref","unstructured":"J. Carreira, A. Zisserman, Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset, in: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017.","DOI":"10.1109\/CVPR.2017.502"},{"key":"10.1016\/j.patcog.2026.114314_b53","series-title":"The 3rd International Conference for Learning Representations","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"10.1016\/j.patcog.2026.114314_b54","series-title":"Consistency-based self-supervised learning for temporal anomaly localization","author":"Panariello","year":"2022"},{"key":"10.1016\/j.patcog.2026.114314_b55","series-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XIII","first-page":"729","article-title":"Self-supervised sparse representation for video anomaly detection","author":"Wu","year":"2022"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012793?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012793?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T12:51:34Z","timestamp":1788526294000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326012793"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":55,"alternative-id":["S0031320326012793"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114314","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MGFN++: Magnitude-contrastive glance-and-focus network for weakly-supervised video anomaly detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114314","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114314"}}