{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:14:10Z","timestamp":1780913650949,"version":"3.54.1"},"reference-count":38,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"2023 Police Foundations Specialized Project","award":["2023JC31"],"award-info":[{"award-number":["2023JC31"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>In the realm of public safety, the automated identification of potential threats from voluminous surveillance streams is pivotal for developing intelligent security systems. Manual monitoring of such massive video feeds is highly inefficient, prone to human fatigue, and often leads to missed detections or false alarms. Leveraging deep learning for automatic anomaly detection is therefore essential to improve response efficiency and mitigate security risks. Weakly supervised video anomaly detection (WS-VAD) has emerged as a critical yet challenging task in this domain. In this study, we propose the Temporal-Enhanced and Visual-Text Adaptive Fusion (TE-VTAF) model for robust WS-VAD. Specifically, a Dynamic Local\u2013Global Temporal Adaptive Module (DLG-TAM) is designed to capture multi-scale temporal dependencies and extract high-level video semantics. Concurrently, a Visual-Text Adaptive Fusion Module (VTAFM) is introduced to aggregate complementary cross-modal features, utilizing a competitive activation mechanism to suppress redundant information and enhance the discriminative power between normal and anomalous events. To further refine the learning process within the Multiple Instance Learning (MIL) framework, we incorporate a Top-K outer bag loss and a K-maxmin inner bag loss. These constraints effectively maximize the inter-class separability while suppressing label noise from normal instances within positive bags, thereby bolstering the detector\u2019s robustness. Extensive experiments demonstrate that the proposed TE-VTAF consistently outperforms state-of-the-art methods on two large-scale benchmarks, achieving an AUC of 88.93% on UCF-Crime and an AP of 85.62% on XD-Violence.<\/jats:p>","DOI":"10.3390\/jimaging12060249","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T02:32:46Z","timestamp":1780885966000},"page":"249","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Temporal-Enhanced and Visual-Text Adaptive Fusion for Weakly Supervised Video Anomaly Detection in Public Safety"],"prefix":"10.3390","volume":"12","author":[{"given":"Jin","family":"Si","sequence":"first","affiliation":[{"name":"Big Data and Network Security Research Institute, Zhejiang Police College, Hangzhou 310053, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qifen","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Information and Network Security, Zhejiang Police College, Hangzhou 310053, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information and Network Security, Zhejiang Police College, Hangzhou 310053, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., and Paluri, M. (2015, January 7\u201313). Learning spatiotemporal features with 3d convolutional networks. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Carreira, J., and Zisserman, A. (2017, January 22\u201325). Quo vadis, action recognition? A new model and the kinetics dataset. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Sultani, W., Chen, C., and Shah, M. (2018, January 18\u201322). Real-world anomaly detection in surveillance videos. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhang, J., Qing, L., and Miao, J. (2019, January 22\u201325). Temporal convolutional network with complementary inner bag loss for weakly supervised anomaly detection. Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan.","DOI":"10.1109\/ICIP.2019.8803657"},{"key":"ref_5","unstructured":"Zhu, Y., and Newsam, S. (2019). Motion-aware feature for improved video anomaly detection. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wu, P., Liu, J., Shi, Y., Sun, Y., Shao, F., Wu, Z., and Yang, Z. (2020). Not only look, but also listen: Learning multimodal violence detection under weak supervision. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref_7","unstructured":"Kim, W., Son, B., and Kim, I. (2021, January 18\u201324). Vilt: Vision-and-language transformer without convolution or region supervision. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_8","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021, January 18\u201324). Learning transferable visual models from natural language supervision. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Joo, H.K., Vo, K., Yamazaki, K., and Le, N. (2023). Clip-tsa: Clip-assisted temporal self-attention for weakly-supervised video anomaly detection. 2023 IEEE International Conference on Image Processing (ICIP), IEEE.","DOI":"10.1109\/ICIP49359.2023.10222289"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Lv, H., Yue, Z., Sun, Q., Luo, B., Cui, Z., and Zhang, H. (2023, January 18\u201322). Unbiased multiple instance learning for weakly supervised video anomaly detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00775"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"104163","DOI":"10.1016\/j.cviu.2024.104163","article-title":"Delving into CLIP latent space for video anomaly recognition","volume":"249","author":"Zanella","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"105560","DOI":"10.1016\/j.dsp.2025.105560","article-title":"VadCLIP++: Dynamic vision-language model for weakly supervised video anomaly detection","volume":"168","author":"Liu","year":"2026","journal-title":"Digit. Signal Process."},{"key":"ref_13","first-page":"12027","article-title":"Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment","volume":"40","author":"Yin","year":"2026","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, M., Sang, J., Lu, Y., and Du, L. (2025). WSVAD-CLIP: Temporally Aware and Prompt Learning with CLIP for Weakly Supervised Video Anomaly Detection. J. Imaging, 11.","DOI":"10.3390\/jimaging11100354"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"111978","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":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhong, J.X., Li, N., Kong, W., Liu, S., Li, T.H., and Li, G. (2019, January 16\u201320). Graph convolutional label noise cleaner: Train a plug-and-play action classifier for anomaly detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00133"},{"key":"ref_17","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.1109\/LSP.2020.3025688","article-title":"A self-reasoning framework for anomaly detection using video-level labels","volume":"27","author":"Zaheer","year":"2020","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Feng, J.C., Hong, F.T., and Zheng, W.S. (2021, January 19\u201325). Mist: Multiple instance self-training framework for video anomaly detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Tian, Y., Pang, G., Chen, Y., Singh, R., Verjans, J.W., and Carneiro, G. (2021, January 11\u201317). Weakly-supervised video anomaly detection with robust temporal feature magnitude learning. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref_21","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. AAAI Conf. Artif. Intell."},{"key":"ref_22","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, W., Ma, K.T., Yew, Z.J., Hur, M., and Khoo, D.A.-A. (2023, January 18\u201322). TEVAD: Improved video anomaly detection with captions. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPRW59228.2023.00587"},{"key":"ref_24","first-page":"6074","article-title":"Vadclip: Adapting vision-language models for weakly supervised video anomaly detection","volume":"38","author":"Wu","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, G., Liu, J., Xu, Z., Chen, X., and Wei, J. (2025). RelVid: Relational Learning with Vision-Language Models for Weakly Video Anomaly Detection. Sensors, 25.","DOI":"10.3390\/s25072037"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhu, T., Yu, Q., Dong, X., Li, S., Liu, Y., and Jiang, J. (2025, January 5\u20138). ProDisc-VAD: An Efficient System for Weakly-Supervised Anomaly Detection in Video Surveillance Applications. Proceedings of the 2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Vienna, Austria.","DOI":"10.1109\/SMC58881.2025.11343488"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"127857","DOI":"10.1016\/j.eswa.2025.127857","article-title":"MMVAD: A vision\u2013language model for cross-domain video anomaly detection with contrastive learning and scale-adaptive frame snippetation","volume":"285","author":"Biswas","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Perreault, H., Bilodeau, G.A., Saunier, N., and Hritier, M. (2020, January 13\u201315). Spotnet: Self-attention multi-task network for object detection. Proceedings of the 2020 17th Conference on Computer and Robot Vision (CRV), Ottawa, ON, Canada.","DOI":"10.1109\/CRV50864.2020.00038"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wan, B., Fang, Y., Xia, X., and Mei, J. (2020, January 6\u201310). Weakly supervised video anomaly detection via center-guided discriminative learning. Proceedings of the 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK.","DOI":"10.1109\/ICME46284.2020.9102722"},{"key":"ref_30","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., and Bradbury, J. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Sapkota, H., and Yu, Q. (2022, January 19\u201324). Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00321"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"22835","DOI":"10.1038\/s41598-024-73462-0","article-title":"Multimodal and multiscale feature fusion for weakly supervised video anomaly detection","volume":"14","author":"Sun","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"5480","DOI":"10.1109\/TCSVT.2024.3350084","article-title":"Weakly-supervised video anomaly detection with snippet anomalous attention","volume":"34","author":"Fan","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, Y., and Yeo, C.K. (2025). Enhancing Weakly Supervised Video Anomaly Detection with Object-Centric Features. Information, 16.","DOI":"10.3390\/info16121042"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"4923","DOI":"10.1109\/TIP.2024.3451935","article-title":"Learning prompt-enhanced context features for weakly-supervised video anomaly detection","volume":"33","author":"Pu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"ref_36","first-page":"481","article-title":"Temporal context and representative feature learning for weakly supervised video anomaly detection","volume":"3","author":"Qiu","year":"2025","journal-title":"J. Inf. Intell."},{"key":"ref_37","first-page":"3769","article-title":"Dual memory units with uncertainty regulation for weakly supervised video anomaly detection","volume":"37","author":"Zhou","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_38","unstructured":"Wu, P., Zhou, X., Pang, G., Yang, Z., Yan, Q., Wang, P., and Zhang, Y. (November, January 28). Weakly supervised video anomaly detection and localization with spatio-temporal prompts. Proceedings of the 32nd ACM International Conference on Multimedia, Melbourne, Australia."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/6\/249\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T09:42:39Z","timestamp":1780911759000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/6\/249"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,6]]},"references-count":38,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["jimaging12060249"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12060249","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,6]]}}}