{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:46:28Z","timestamp":1776786388280,"version":"3.51.2"},"reference-count":62,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"name":"British Telecom Ireland Innovation Centre"},{"name":"Invest Northern Ireland (Invest NI) and BT"},{"name":"Major Fundamental Research Project of Shandong","award":["ZR2024ZD03"],"award-info":[{"award-number":["ZR2024ZD03"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>\n                    In recent years, Video Anomaly Detection (VAD) has shifted from conventional appearance-based modeling to semantically driven frameworks empowered by LLMs. Traditional reconstruction- and prediction-based methods, relying on motion or appearance patterns learned from normal data, often misclassify previously unseen yet semantically normal events as anomalies. To address this limitation, we propose SOR-BDNet (Semantic-Optical Representation with Boundary Detection Network), an annotation-free multimodal VAD framework that jointly leverages visual appearance and motion dynamics to generate interpretable semantic representations at the frame level. Specifically, we employ RAFT to estimate dense motion fields and concatenate the resulting flow maps with RGB images to form unified spatiotemporal inputs. These fused representations are fed into a GPT-4o-based module that generates semantic captions capturing object semantics and motion cues. Anomalies are detected by measuring semantic deviations from a memory bank constructed from normal captions. To further refine temporal boundaries, we design a boundary refinement module that integrates visual continuity constraints with contrastive feature learning based on a Swin Transformer backbone. Extensive experiments on four challenging benchmarks\u2014UCSD-Ped2, Avenue, ShanghaiTech, and UCF-Crime\u2014demonstrate that SOR-BDNet achieves frame-level accuracies of 97.96%, 82.86%, 87.36%, and 85.64%, respectively. These results highlight the robustness and scalability of the proposed framework, while significantly improving interpretability and generalization across diverse real-world surveillance scenarios. The source code and pretrained models are available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/syi-coder\/SOR-BDNet-Semantic-Optical-Representation-for-Boundary-Aware-Video-Anomaly-Detection-with-GPT-4o\">https:\/\/github.com\/syi-coder\/SOR-BDNet-Semantic-Optical-Representation-for-Boundary-Aware-Video-Anomaly-Detection-with-GPT-4o<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1145\/3801156","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T10:53:01Z","timestamp":1773399181000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SOR-BDNet: Semantic-Optical Representation for Boundary-Aware Video Anomaly Detection with GPT-4o"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3981-4496","authenticated-orcid":false,"given":"Yi","family":"Sun","sequence":"first","affiliation":[{"name":"Ulster University - Belfast Campus, Belfast, United Kingdom of Great Britain and Northern Ireland and Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8243-2223","authenticated-orcid":false,"given":"Bryan","family":"W. Scotney","sequence":"additional","affiliation":[{"name":"Ulster University - Belfast Campus, Belfast, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9644-9723","authenticated-orcid":false,"given":"Xiushan","family":"Nie","sequence":"additional","affiliation":[{"name":"Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7236-8715","authenticated-orcid":false,"given":"Xingbo","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4821-6404","authenticated-orcid":false,"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ulster University - Belfast Campus, Belfast, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4874-7176","authenticated-orcid":false,"given":"Lanting","family":"Qiu","sequence":"additional","affiliation":[{"name":"Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00261"},{"key":"e_1_3_1_3_2","first-page":"132","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"AlMarri Salem","year":"2024","unstructured":"Salem AlMarri, Muhammad Zaigham Zaheer, and Karthik Nandakumar. 2024. A multi-head approach with shuffled segments for weakly-supervised video anomaly detection. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 132\u2013142."},{"key":"e_1_3_1_4_2","unstructured":"Kirolos Ataallah Xiaoqian Shen Eslam Abdelrahman Essam Sleiman Deyao Zhu Jian Ding and Mohamed Elhoseiny. 2024. Minigpt4-video: Advancing multimodal llms for video understanding with interleaved visual-textual tokens. arXiv:2404.03413. Retrieved from https:\/\/arxiv.org\/abs\/2404.03413"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3321801"},{"issue":"1998","key":"e_1_3_1_6_2","first-page":"1","article-title":"Linear discriminant analysis-a brief tutorial","volume":"18","author":"Balakrishnama Suresh","year":"1998","unstructured":"Suresh Balakrishnama and Aravind Ganapathiraju. 1998. Linear discriminant analysis-a brief tutorial. Institute for Signal and Information Processing 18, 1998 (1998), 1\u20138.","journal-title":"Institute for Signal and Information Processing"},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","first-page":"70882","DOI":"10.1109\/ACCESS.2025.3560767","article-title":"Enhancing weakly-supervised video anomaly detection with temporal constraints","author":"Caetano Francisco","year":"2025","unstructured":"Francisco Caetano, Pedro Carvalho, Christina Mastralexi, and Jaime S. Cardoso. 2025. Enhancing weakly-supervised video anomaly detection with temporal constraints. IEEE Access 13 (2025), 70882\u201370894.","journal-title":"IEEE Access"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01953"},{"key":"e_1_3_1_9_2","doi-asserted-by":"crossref","first-page":"107969","DOI":"10.1016\/j.patcog.2021.107969","article-title":"NM-GAN: Noise-modulated generative adversarial network for video anomaly detection","volume":"116","author":"Chen Dongyue","year":"2021","unstructured":"Dongyue Chen, Lingyi Yue, Xingya Chang, Ming Xu, and Tong Jia. 2021. NM-GAN: Noise-modulated generative adversarial network for video anomaly detection. Pattern Recognition 116 (2021), 107969.","journal-title":"Pattern Recognition"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01734"},{"key":"e_1_3_1_11_2","doi-asserted-by":"crossref","first-page":"108703","DOI":"10.1016\/j.patcog.2022.108703","article-title":"Unsupervised video anomaly detection via normalizing flows with implicit latent features","volume":"129","author":"Cho MyeongAh","year":"2022","unstructured":"MyeongAh Cho, Taeoh Kim, Woo Jin Kim, Suhwan Cho, and Sangyoun Lee. 2022. Unsupervised video anomaly detection via normalizing flows with implicit latent features. Pattern Recognition 129 (2022), 108703.","journal-title":"Pattern Recognition"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00266"},{"key":"e_1_3_1_13_2","first-page":"18793","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Du Hang","year":"2024","unstructured":"Hang Du, Sicheng Zhang, Binzhu Xie, Guoshun Nan, Jiayang Zhang, Junrui Xu, Hangyu Liu, Sicong Leng, Jiangming Liu, Hehe Fan, et\u00a0al. 2024. Uncovering what why and how: A comprehensive benchmark for causation understanding of video anomaly. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 18793\u201318803."},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2960654"},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","first-page":"102920","DOI":"10.1016\/j.cviu.2020.102920","article-title":"Video anomaly detection and localization via gaussian mixture fully convolutional variational autoencoder","volume":"195","author":"Fan Yaxiang","year":"2020","unstructured":"Yaxiang Fan, Gongjian Wen, Deren Li, Shaohua Qiu, Martin D. Levine, and Fei Xiao. 2020. Video anomaly detection and localization via gaussian mixture fully convolutional variational autoencoder. Computer Vision and Image Understanding 195 (2020), 102920.","journal-title":"Computer Vision and Image Understanding"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"e_1_3_1_17_2","first-page":"1","volume-title":"Proceedings of the ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Gao Shibo","year":"2025","unstructured":"Shibo Gao, Peipei Yang, and Linlin Huang. 2025. SUVAD: Semantic understanding based video anomaly detection using MLLM. In Proceedings of the ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1\u20135."},{"key":"e_1_3_1_18_2","first-page":"1873","article-title":"Video anomaly detection based on multi-scale optical flow spatio-temporal enhancement and normality mining","author":"He Qiang","year":"2024","unstructured":"Qiang He, Ruinian Shi, Linlin Chen, and Lianzhi Huo. 2024. Video anomaly detection based on multi-scale optical flow spatio-temporal enhancement and normality mining. International Journal of Machine Learning and Cybernetics 16 (2024), 1873\u20131888.","journal-title":"International Journal of Machine Learning and Cybernetics"},{"issue":"2","key":"e_1_3_1_19_2","first-page":"507","article-title":"Anomaly detection in video via independently recurrent neural network and variational auto-encoder network","volume":"43","author":"Jia Q.","year":"2023","unstructured":"Q. Jia, L. Wang, and W. Wang. 2023. Anomaly detection in video via independently recurrent neural network and variational auto-encoder network. Journal of Computer Applications 43, 2 (2023), 507.","journal-title":"Journal of Computer Applications"},{"key":"e_1_3_1_20_2","first-page":"301346","article-title":"A semi-supervised deep learning based video anomaly detection framework using RGB-D for surveillance of real-world critical environments","volume":"40","author":"Khaire Pushpajit","year":"2022","unstructured":"Pushpajit Khaire and Praveen Kumar. 2022. A semi-supervised deep learning based video anomaly detection framework using RGB-D for surveillance of real-world critical environments. Forensic Science International: Digital Investigation 40 (2022), 301346.","journal-title":"Forensic Science International: Digital Investigation"},{"key":"e_1_3_1_21_2","first-page":"50","volume-title":"Proceedings of the 2023 International Conference on Communication System, Computing and IT Applications (CSCITA)","author":"Kumar Ankit","year":"2023","unstructured":"Ankit Kumar and Manju Khari. 2023. Efficient video anomaly detection using residual variational autoencoder. In Proceedings of the 2023 International Conference on Communication System, Computing and IT Applications (CSCITA). IEEE, 50\u201355."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03613-1"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2695105"},{"key":"e_1_3_1_24_2","first-page":"12888","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In Proceedings of the International Conference on Machine Learning. PMLR, 12888\u201312900."},{"key":"e_1_3_1_25_2","unstructured":"KunChang Li Yinan He Yi Wang Yizhuo Li Wenhai Wang Ping Luo Yali Wang Limin Wang and Yu Qiao. 2023. Videochat: Chat-centric video understanding. arXiv:2305.06355. Retrieved from https:\/\/arxiv.org\/abs\/2305.06355"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"issue":"1","key":"e_1_3_1_27_2","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TPAMI.2013.111","article-title":"Anomaly detection and localization in crowded scenes","volume":"36","author":"Li Weixin","year":"2013","unstructured":"Weixin Li, Vijay Mahadevan, and Nuno Vasconcelos. 2013. Anomaly detection and localization in crowded scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence 36, 1 (2013), 18\u201332.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"e_1_3_1_28_2","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1007\/s10489-025-06485-3","article-title":"Multi-scale spatiotemporal normality learning for unsupervised video anomaly detection","volume":"55","author":"Liu Caitian","year":"2025","unstructured":"Caitian Liu, Linxiao Gong, and Xiong Chen. 2025. Multi-scale spatiotemporal normality learning for unsupervised video anomaly detection. Applied Intelligence 55, 7 (2025), 584.","journal-title":"Applied Intelligence"},{"key":"e_1_3_1_29_2","doi-asserted-by":"crossref","first-page":"1197434","DOI":"10.3389\/frsc.2023.1197434","article-title":"Unsupervised video anomaly detection in UAVs: A new approach based on learning and inference","volume":"5","author":"Liu Gang","year":"2023","unstructured":"Gang Liu, Lisheng Shu, Yuhui Yang, and Chen Jin. 2023. Unsupervised video anomaly detection in UAVs: A new approach based on learning and inference. Frontiers in Sustainable Cities 5 (2023), 1197434.","journal-title":"Frontiers in Sustainable Cities"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3129349"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01517"},{"key":"e_1_3_1_36_2","unstructured":"Muhammad Maaz Hanoona Rasheed Salman Khan and Fahad Shahbaz Khan. 2023. Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv:2306.05424. Retrieved from https:\/\/arxiv.org\/abs\/2306.05424"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01227"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkg509"},{"key":"e_1_3_1_39_2","first-page":"4923","article-title":"Learning prompt-enhanced context features for weakly-supervised video anomaly detection","author":"Pu Yujiang","year":"2024","unstructured":"Yujiang Pu, Xiaoyu Wu, Lulu Yang, and Shengjin Wang. 2024. Learning prompt-enhanced context features for weakly-supervised video anomaly detection. IEEE Transactions on Image Processing 33 (2024), 4923\u20134936.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_1_40_2","first-page":"8748","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning. PmLR, 8748\u20138763."},{"key":"e_1_3_1_41_2","first-page":"626","article-title":"EM algorithms for PCA and SPCA","volume":"10","author":"Roweis Sam","year":"1997","unstructured":"Sam Roweis. 1997. EM algorithms for PCA and SPCA. Advances in Neural Information Processing Systems 10 (1997), 626\u2013632.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_42_2","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 Haoyue","year":"2023","unstructured":"Haoyue Shi, Le Wang, Sanping Zhou, Gang Hua, and Wei Tang. 2023. Abnormal ratios guided multi-phase self-training for weakly-supervised video anomaly detection. IEEE Transactions on Multimedia 26 (2023), 5575\u20135587.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_1_43_2","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. Advances in Neural Information Processing Systems 27 (2014), 568\u2013576.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3566695"},{"key":"e_1_3_1_46_2","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 Yao","year":"2020","unstructured":"Yao Tang, Lin Zhao, Shanshan Zhang, Chen Gong, Guangyu Li, and Jian Yang. 2020. Integrating prediction and reconstruction for anomaly detection. Pattern Recognition Letters 129 (2020), 123\u2013130.","journal-title":"Pattern Recognition Letters"},{"key":"e_1_3_1_47_2","first-page":"10160","article-title":"Feature reconstruction with disruption for unsupervised video anomaly detection","author":"Tao Chenchen","year":"2024","unstructured":"Chenchen Tao, Chong Wang, Sunqi Lin, Suhang Cai, Di Li, and Jiangbo Qian. 2024. Feature reconstruction with disruption for unsupervised video anomaly detection. IEEE Transactions on Multimedia 26 (2024), 10160\u201310173.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_1_48_2","unstructured":"Yiyi Tao Zhuoyue Wang Hang Zhang and Lun Wang. 2024. Nevlp: Noise-robust framework for efficient vision-language pre-training. arXiv:2409.09582. Retrieved from https:\/\/arxiv.org\/abs\/2409.09582"},{"key":"e_1_3_1_49_2","first-page":"402","volume-title":"Proceedings of the 16th European Conference on Computer Vision (ECCV \u201920), Part II","author":"Teed Zachary","year":"2020","unstructured":"Zachary Teed and Jia Deng. 2020. Raft: Recurrent all-pairs field transforms for optical flow. In Proceedings of the 16th European Conference on Computer Vision (ECCV \u201920), Part II. Springer, 402\u2013419."},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43153-1_5"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083152"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459207"},{"key":"e_1_3_1_53_2","first-page":"729","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Wu Jhih-Ciang","year":"2022","unstructured":"Jhih-Ciang Wu, He-Yen Hsieh, Ding-Jie Chen, Chiou-Shann Fuh, and Tyng-Luh Liu. 2022. Self-supervised sparse representation for video anomaly detection. In Proceedings of the European Conference on Computer Vision. Springer, 729\u2013745."},{"key":"e_1_3_1_54_2","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 Peng","year":"2021","unstructured":"Peng Wu and Jing Liu. 2021. Learning causal temporal relation and feature discrimination for anomaly detection. IEEE Transactions on Image Processing 30 (2021), 3513\u20133527.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_1_55_2","first-page":"9161","article-title":"Distributed learning for privacy-preserving semi-supervised video anomaly detection","author":"Xie Xiao-Dong","year":"2025","unstructured":"Xiao-Dong Xie, Yu-Wei Zhan, Zhen-Xiang Ma, Hong-Mei Liu, Zhen-Duo Chen, Xin Luo, and Xin-Shun Xu. 2025. Distributed learning for privacy-preserving semi-supervised video anomaly detection. IEEE Transactions on Circuits and Systems for Video Technology 35, 9 (2025), 9161\u20139174.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"e_1_3_1_56_2","first-page":"13987","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yu Guang","year":"2022","unstructured":"Guang Yu, Siqi Wang, Zhiping Cai, Xinwang Liu, Chuanfu Xu, and Chengkun Wu. 2022. Deep anomaly discovery from unlabeled videos via normality advantage and self-paced refinement. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 13987\u201313998."},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01753"},{"key":"e_1_3_1_58_2","doi-asserted-by":"crossref","unstructured":"Hang Zhang Xin Li and Lidong Bing. 2023. Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv:2306.02858. Retrieved from https:\/\/arxiv.org\/abs\/2306.02858","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"e_1_3_1_59_2","unstructured":"Huaxin Zhang Xiaohao Xu Xiang Wang Jialong Zuo Chuchu Han Xiaonan Huang Changxin Gao Yuehuan Wang and Nong Sang. 2024. Holmes-vad: Towards unbiased and explainable video anomaly detection via multi-modal llm. arXiv:2406.12235. Retrieved from https:\/\/arxiv.org\/abs\/2406.12235"},{"key":"e_1_3_1_60_2","doi-asserted-by":"crossref","first-page":"103416","DOI":"10.1016\/j.cviu.2022.103416","article-title":"Detecting abnormality with separated foreground and background: Mutual generative adversarial networks for video abnormal event detection","volume":"219","author":"Zhang Zhi","year":"2022","unstructured":"Zhi Zhang, Sheng-Hua Zhong, Ahmed Fares, and Yan Liu. 2022. Detecting abnormality with separated foreground and background: Mutual generative adversarial networks for video abnormal event detection. Computer Vision and Image Understanding 219 (2022), 103416.","journal-title":"Computer Vision and Image Understanding"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00133"},{"key":"e_1_3_1_62_2","first-page":"1961","article-title":"Inter-clip feature similarity based weakly supervised video anomaly detection via multi-scale temporal MLP","author":"Zhong Yuanhong","year":"2024","unstructured":"Yuanhong Zhong, Ruyue Zhu, Ge Yan, Ping Gan, Xuerui Shen, and Dong Zhu. 2024. Inter-clip feature similarity based weakly supervised video anomaly detection via multi-scale temporal MLP. IEEE Transactions on Circuits and Systems for Video Technology 35, 2 (2024) 1961\u20131970.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2900907"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3801156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:57:27Z","timestamp":1776783447000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801156"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":62,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3801156"],"URL":"https:\/\/doi.org\/10.1145\/3801156","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]},"assertion":[{"value":"2025-06-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}