{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T08:10:52Z","timestamp":1764144652861,"version":"3.46.0"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672305"],"award-info":[{"award-number":["61672305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s10489-025-06975-4","type":"journal-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T06:01:03Z","timestamp":1762581663000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MMI-FM: Multimodal Interaction and Fusion Mechanism for Video Anomaly Detection"],"prefix":"10.1007","volume":"55","author":[{"given":"Binghui","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7983-5061","authenticated-orcid":false,"given":"Chuanxu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajiong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yishuo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,8]]},"reference":[{"issue":"3","key":"6975_CR1","doi-asserted-by":"publisher","first-page":"3240","DOI":"10.1007\/s10489-022-03613-1","volume":"53","author":"V-T Le","year":"2023","unstructured":"Le V-T, Kim Y-G (2023) Attention-based residual autoencoder for video anomaly detection. Appl Intell 53(3):3240\u20133254","journal-title":"Appl Intell"},{"issue":"1","key":"6975_CR2","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1007\/s10489-022-03488-2","volume":"53","author":"C Li","year":"2023","unstructured":"Li C, Li H, Zhang G (2023) Future frame prediction based on generative assistant discriminative network for anomaly detection. Appl Intell 53(1):542\u2013559","journal-title":"Appl Intell"},{"issue":"7","key":"6975_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3645101","volume":"56","author":"Y Liu","year":"2024","unstructured":"Liu Y, Yang D, Wang Y, Liu J, Liu J, Boukerche A, Sun P, Song L (2024) Generalized video anomaly event detection: Systematic taxonomy and comparison of deep models. ACM Comput Surv 56(7):1\u201338","journal-title":"ACM Comput Surv"},{"key":"6975_CR4","doi-asserted-by":"crossref","unstructured":"Georgescu M\u00a0I, Ionescu R\u00a0T, Khan F\u00a0S, Popescu M, Shah M (2021) A background-agnostic framework with adversarial training for abnormal event detection in video. IEEE Trans Pattern Anal Mach Intell, 44(9):4505\u20134523.","DOI":"10.1109\/TPAMI.2021.3074805"},{"key":"6975_CR5","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":"6975_CR6","doi-asserted-by":"crossref","unstructured":"Liu Z, Nie Y, Long C, Zhang Q, Li G (2021) A hybrid video anomaly detection framework via memory-augmented flow reconstruction and flow-guided frame prediction. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 13588\u201313597","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"6975_CR7","doi-asserted-by":"crossref","unstructured":"Gong D, Liu L, Le V, Saha B, Mansour M\u00a0R, Venkatesh S, van\u00a0den Hengel A (2019) Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1705\u20131714.","DOI":"10.1109\/ICCV.2019.00179"},{"key":"6975_CR8","doi-asserted-by":"crossref","unstructured":"Nguyen T-N, Meunier J (2019) Anomaly detection in video sequence with appearance-motion correspondence. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1273\u20131283.","DOI":"10.1109\/ICCV.2019.00136"},{"key":"6975_CR9","doi-asserted-by":"crossref","unstructured":"Yu G, Wang S, Cai Z, Zhu E, Xu C, Yin J, Kloft M (2020) Cloze test helps: Effective video anomaly detection via learning to complete video events. In: Proceedings of the 28th ACM international conference on multimedia, pp 583\u2013591.","DOI":"10.1145\/3394171.3413973"},{"key":"6975_CR10","doi-asserted-by":"crossref","unstructured":"Feng X, Song D, Chen Y, Chen Z, Ni J, Chen H (2021) Convolutional transformer based dual discriminator generative adversarial networks for video anomaly detection. In: Proceedings of the 29th ACM International Conference on Multimedia, pp 5546\u20135554","DOI":"10.1145\/3474085.3475693"},{"key":"6975_CR11","doi-asserted-by":"crossref","unstructured":"Ristea N-C, Croitoru F-A, Ionescu R\u00a0T, Popescu M, Khan F\u00a0S, Shah M, et\u00a0al (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"},{"key":"6975_CR12","doi-asserted-by":"crossref","unstructured":"Flaborea A, di Melendugno GM, D\u2019Arrigo S, Sterpa MA, Sampieri A, Galasso F (2024) Contracting skeletal kinematics for human-related video anomaly detection. Pattern Recogn, 156:110817","DOI":"10.1016\/j.patcog.2024.110817"},{"key":"6975_CR13","doi-asserted-by":"crossref","unstructured":"Zhou H, Cai J, Ye Y, Feng Y, Gao C, Yu J, Song Z, Yang W (2024) Video anomaly detection with motion and appearance guided patch diffusion model. arXiv:2412.09026","DOI":"10.1609\/aaai.v39i10.33169"},{"key":"6975_CR14","doi-asserted-by":"crossref","unstructured":"Huang X, Zhao C, Wu Z (2023) A video anomaly detection framework based on appearance-motion semantics representation consistency. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 1\u20135. IEEE,","DOI":"10.1109\/ICASSP49357.2023.10097199"},{"key":"6975_CR15","doi-asserted-by":"crossref","unstructured":"Xiao J, Ji G (2023) Divide and conquer in video anomaly detection: A comprehensive review and new approach. In: 2023 China Automation Congress (CAC), pp 8553\u20138558. IEEE,","DOI":"10.1109\/CAC59555.2023.10451821"},{"issue":"3","key":"6975_CR16","doi-asserted-by":"publisher","first-page":"1344","DOI":"10.3390\/app11031344","volume":"11","author":"S Dubey","year":"2021","unstructured":"Dubey S, Boragule A, Gwak J, Jeon M (2021) Anomalous event recognition in videos based on joint learning of motion and appearance with multiple ranking measures. Appl Sci 11(3):1344","journal-title":"Appl Sci"},{"key":"6975_CR17","doi-asserted-by":"publisher","first-page":"2178","DOI":"10.1109\/LSP.2022.3216500","volume":"29","author":"D Wei","year":"2022","unstructured":"Wei D, Liu Y, Zhu X, Liu J, Zeng X (2022) Msaf: Multimodal supervise-attention enhanced fusion for video anomaly detection. IEEE Signal Process Lett 29:2178\u20132182","journal-title":"IEEE Signal Process Lett"},{"issue":"1","key":"6975_CR18","doi-asserted-by":"publisher","first-page":"22835","DOI":"10.1038\/s41598-024-73462-0","volume":"14","author":"W Sun","year":"2024","unstructured":"Sun W, Cao L, Guo Y, Kangning D (2024) Multimodal and multiscale feature fusion for weakly supervised video anomaly detection. Sci Rep 14(1):22835","journal-title":"Sci Rep"},{"key":"6975_CR19","doi-asserted-by":"crossref","unstructured":"Cong Y, Yuan J, Liu J (2011) Sparse reconstruction cost for abnormal event detection. In: CVPR 2011, pp 3449\u20133456. IEEE,","DOI":"10.1109\/CVPR.2011.5995434"},{"key":"6975_CR20","doi-asserted-by":"crossref","unstructured":"Kratz L, Nishino K (2009) Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In: 2009 IEEE conference on computer vision and pattern recognition, pp 1446\u20131453. IEEE,","DOI":"10.1109\/CVPR.2009.5206771"},{"key":"6975_CR21","doi-asserted-by":"crossref","unstructured":"Zhao Y, Deng B, Shen C, Liu Y, Lu H, Hua X-S (2017) Spatio-temporal autoencoder for video anomaly detection. In: Proceedings of the 25th ACM international conference on Multimedia, pp 1933\u20131941,","DOI":"10.1145\/3123266.3123451"},{"key":"6975_CR22","doi-asserted-by":"crossref","unstructured":"Lowe D\u00a0G (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis, 60:91\u2013110","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"6975_CR23","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.cviu.2018.02.006","volume":"172","author":"M Sabokrou","year":"2018","unstructured":"Sabokrou M, Fayyaz M, Fathy M, Moayed Z, Klette R (2018) Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes. Comput Vis Image Underst 172:88\u201397","journal-title":"Comput Vis Image Underst"},{"key":"6975_CR24","doi-asserted-by":"crossref","unstructured":"Eskin E, Arnold A, Prerau M, Portnoy L, Stolfo S (2002) A geometric framework for unsupervised anomaly detection: Detecting intrusions in unlabeled data. Appl Data Mining Comput Secur, pp 77\u2013101","DOI":"10.1007\/978-1-4615-0953-0_4"},{"key":"6975_CR25","doi-asserted-by":"crossref","unstructured":"Latecki L\u00a0J, Lazarevic A, Pokrajac D (2007) Outlier detection with kernel density functions. In: International workshop on machine learning and data mining in pattern recognition, pp 61\u201375. Springer,","DOI":"10.1007\/978-3-540-73499-4_6"},{"key":"6975_CR26","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/s00180-012-0374-5","volume":"28","author":"M Glodek","year":"2013","unstructured":"Glodek M, Schels M, Schwenker F (2013) Ensemble gaussian mixture models for probability density estimation. Comput Stat 28:127\u2013138","journal-title":"Comput Stat"},{"key":"6975_CR27","doi-asserted-by":"crossref","unstructured":"Hinami R, Mei T, Satoh S (2017) Joint detection and recounting of abnormal events by learning deep generic knowledge. In: Proceedings of the IEEE international conference on computer vision, pp 3619\u20133627","DOI":"10.1109\/ICCV.2017.391"},{"key":"6975_CR28","doi-asserted-by":"crossref","unstructured":"Mehran R, Oyama A, Shah M (2009) Abnormal crowd behavior detection using social force model. In: 2009 IEEE conference on computer vision and pattern recognition, pp 935\u2013942. IEEE","DOI":"10.1109\/CVPR.2009.5206641"},{"key":"6975_CR29","doi-asserted-by":"crossref","unstructured":"Cheng K-W, Chen Y-T, Fang W-H (2015) Video anomaly detection and localization using hierarchical feature representation and gaussian process regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2909\u20132917.","DOI":"10.1109\/CVPR.2015.7298909"},{"key":"6975_CR30","doi-asserted-by":"crossref","unstructured":"Anti\u0107 B, Ommer B (2011) Video parsing for abnormality detection. In: 2011 International conference on computer vision, pp 2415\u20132422. IEEE,","DOI":"10.1109\/ICCV.2011.6126525"},{"key":"6975_CR31","doi-asserted-by":"crossref","unstructured":"Hasan M, Choi J, Neumann J, Roy-Chowdhury A\u00a0K, Davis L\u00a0S (2016) Learning temporal regularity in video sequences. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 733\u2013742","DOI":"10.1109\/CVPR.2016.86"},{"key":"6975_CR32","doi-asserted-by":"crossref","unstructured":"Li Z, Li N, Jiang K, Ma Z, Wei X, Hong X, Gong Y (2020) Superpixel masking and inpainting for self-supervised anomaly detection. In: Bmvc,","DOI":"10.5244\/C.34.77"},{"key":"6975_CR33","doi-asserted-by":"crossref","unstructured":"Luo W, Liu W, Gao S (2017) A revisit of sparse coding based anomaly detection in stacked rnn framework. In: Proceedings of the IEEE international conference on computer vision, pp 341\u2013349,","DOI":"10.1109\/ICCV.2017.45"},{"key":"6975_CR34","doi-asserted-by":"crossref","unstructured":"Markovitz A, Sharir G, Friedman I, Zelnik-Manor L, Avidan S (2020) Graph embedded pose clustering for anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10539\u201310547,","DOI":"10.1109\/CVPR42600.2020.01055"},{"key":"6975_CR35","doi-asserted-by":"crossref","unstructured":"Morais R, Le V, Tran T, Saha B, Mansour M, Venkatesh S (2019) Learning regularity in skeleton trajectories for anomaly detection in videos. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11996\u201312004","DOI":"10.1109\/CVPR.2019.01227"},{"key":"6975_CR36","doi-asserted-by":"crossref","unstructured":"Yu J, Lee Y, Yow K\u00a0C, Jeon M, Pedrycz W (2021) Abnormal event detection and localization via adversarial event prediction. IEEE Trans Neural Netw Learn Syst, 33(8):3572\u20133586","DOI":"10.1109\/TNNLS.2021.3053563"},{"key":"6975_CR37","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/TMM.2020.3046884","volume":"24","author":"F Ye","year":"2020","unstructured":"Ye F, Huang C, Cao J, Li M, Zhang Y, Cewu L (2020) Attribute restoration framework for anomaly detection. IEEE Trans Multimed 24:116\u2013127","journal-title":"IEEE Trans Multimed"},{"issue":"8","key":"6975_CR38","doi-asserted-by":"publisher","first-page":"2946","DOI":"10.3390\/s22082946","volume":"22","author":"R Vrskova","year":"2022","unstructured":"Vrskova R, Hudec R, Kamencay P, Sykora P (2022) A new approach for abnormal human activities recognition based on convlstm architecture. Sensors 22(8):2946","journal-title":"Sensors"},{"key":"6975_CR39","doi-asserted-by":"crossref","unstructured":"Park H, Noh J, Ham B (2020) Learning memory-guided normality for anomaly detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14372\u201314381","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"6975_CR40","doi-asserted-by":"crossref","unstructured":"Ye M, Peng X, Gan W, Wu W, Qiao Y (2019) Anopcn: Video anomaly detection via deep predictive coding network. In: Proceedings of the 27th ACM international conference on multimedia, pp 1805\u20131813,","DOI":"10.1145\/3343031.3350899"},{"key":"6975_CR41","doi-asserted-by":"crossref","unstructured":"Chang Y, Tu Z, Xie W, Yuan J (2020) Clustering driven deep autoencoder for video anomaly detection. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August, 2020, Proceedings, Part XV 16, pp 329\u2013345. Springer,","DOI":"10.1007\/978-3-030-58555-6_20"},{"key":"6975_CR42","doi-asserted-by":"crossref","unstructured":"Yan C, Zhang S, Liu Y, Pang G, Wang W (2023) Feature prediction diffusion model for video anomaly detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 5527\u20135537,","DOI":"10.1109\/ICCV51070.2023.00509"},{"key":"6975_CR43","unstructured":"Kanu-Asiegbu A\u00a0M, Vasudevan R, Du X (2022) Bipoco: Bi-directional trajectory prediction with pose constraints for pedestrian anomaly detection. arXiv:2207.02281,"},{"key":"6975_CR44","doi-asserted-by":"crossref","unstructured":"Sato F, Hachiuma R, Sekii T (2023) Prompt-guided zero-shot anomaly action recognition using pretrained deep skeleton features. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6471\u20136480,","DOI":"10.1109\/CVPR52729.2023.00626"},{"key":"6975_CR45","doi-asserted-by":"crossref","unstructured":"Lin L, Zhang J, Liu J (2023) Actionlet-dependent contrastive learning for unsupervised skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 2363\u20132372,","DOI":"10.1109\/CVPR52729.2023.00234"},{"key":"6975_CR46","doi-asserted-by":"crossref","unstructured":"He B, Wang J, Qiu J, Bui T, Shrivastava A, Wang Z (2023) Align and attend: Multimodal summarization with dual contrastive losses. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14867\u201314878,","DOI":"10.1109\/CVPR52729.2023.01428"},{"key":"6975_CR47","doi-asserted-by":"crossref","unstructured":"Liu Y, Sun H, Guan W, Xia Y, Zhao Z (2022a) Discriminative feature representation based on cascaded attention network with adversarial joint loss for speech emotion recognition. In: INTERSPEECH, pp 4750\u20134754,","DOI":"10.21437\/Interspeech.2022-11480"},{"issue":"8","key":"6975_CR48","doi-asserted-by":"publisher","first-page":"5171","DOI":"10.1109\/TII.2021.3122801","volume":"18","author":"C Huang","year":"2021","unstructured":"Huang C, Zhihao W, Wen J, Yong X, Jiang Q, Wang Y (2021) Abnormal event detection using deep contrastive learning for intelligent video surveillance system. IEEE Trans Industr Inf 18(8):5171\u20135179","journal-title":"IEEE Trans Industr Inf"},{"key":"6975_CR49","doi-asserted-by":"publisher","first-page":"4067","DOI":"10.1109\/TMM.2021.3112814","volume":"24","author":"S Chang","year":"2021","unstructured":"Chang S, Li Y, Shen S, Feng J, Zhou Z (2021) Contrastive attention for video anomaly detection. IEEE Trans Multimed 24:4067\u20134076","journal-title":"IEEE Trans Multimed"},{"key":"6975_CR50","doi-asserted-by":"crossref","unstructured":"Fioresi J, Dave I\u00a0R, Shah M (2023) Ted-spad: Temporal distinctiveness for self-supervised privacy-preservation for video anomaly detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 13598\u201313609,","DOI":"10.1109\/ICCV51070.2023.01251"},{"key":"6975_CR51","first-page":"12980","volume":"33","author":"Self-supervised learning by compressing representations","year":"2020","unstructured":"Self-supervised learning by compressing representations (2020) Soroush Abbasi Koohpayegani, Ajinkya Tejankar, and Hamed Pirsiavash. Compress. Adv Neural Inf Process Syst 33:12980\u201312992","journal-title":"Adv Neural Inf Process Syst"},{"key":"6975_CR52","doi-asserted-by":"crossref","unstructured":"Passalis N, Tefas A (2018) Learning deep representations with probabilistic knowledge transfer. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 268\u2013284,","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"6975_CR53","first-page":"3135","volume":"34","author":"J Ouyang","year":"2021","unstructured":"Ouyang J, Hui W, Wang M, Zhou W, Li H (2021) Contextual similarity aggregation with self-attention for visual re-ranking. Adv Neural Inf Process Syst 34:3135\u20133148","journal-title":"Adv Neural Inf Process Syst"},{"key":"6975_CR54","doi-asserted-by":"crossref","unstructured":"Wu H, Wang M, Zhou W, Li H, Tian Q (2022) Contextual similarity distillation for asymmetric image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 9489\u20139498,","DOI":"10.1109\/CVPR52688.2022.00927"},{"key":"6975_CR55","doi-asserted-by":"crossref","unstructured":"Tejankar A, Koohpayegani S\u00a0A, Pillai V, Favaro P, Pirsiavash H (2021) Isd: Self-supervised learning by iterative similarity distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 9609\u20139618,","DOI":"10.1109\/ICCV48922.2021.00947"},{"key":"6975_CR56","doi-asserted-by":"crossref","unstructured":"Fang H-S, Xie S, Tai Y-W, Lu C (2017) Rmpe: Regional multi-person pose estimation. In: Proceedings of the IEEE international conference on computer vision, pp 2334\u20132343,","DOI":"10.1109\/ICCV.2017.256"},{"key":"6975_CR57","doi-asserted-by":"crossref","unstructured":"He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9729\u20139738,","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"6975_CR58","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":"6975_CR59","unstructured":"Hendrycks D, Mazeika M, Dietterich T (2018) Deep anomaly detection with outlier exposure. arXiv:1812.04606,"},{"key":"6975_CR60","doi-asserted-by":"crossref","unstructured":"Lee S, Kim H\u00a0G, Ro Y\u00a0M (2018) Stan: Spatio-temporal adversarial networks for abnormal event detection. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 1323\u20131327. IEEE,","DOI":"10.1109\/ICASSP.2018.8462388"},{"key":"6975_CR61","doi-asserted-by":"crossref","unstructured":"Lv H, Chen C, Cui Z, Xu C, Li Y, Yang J (2021) Learning normal dynamics in videos with meta prototype network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15425\u201315434,","DOI":"10.1109\/CVPR46437.2021.01517"},{"key":"6975_CR62","doi-asserted-by":"crossref","unstructured":"Luo W, Liu W, Gao S (2021a) Normal graph: Spatial temporal graph convolutional networks based prediction network for skeleton based video anomaly detection. Neurocomputing, 444:332\u2013337,","DOI":"10.1016\/j.neucom.2019.12.148"},{"key":"6975_CR63","first-page":"938","volume":"35","author":"R Cai","year":"2021","unstructured":"Cai R, Zhang H, Liu W, Gao S, Hao Z (2021) Appearance-motion memory consistency network for video anomaly detection. In: Proceedings of the AAAI conference on artificial intelligence 35:938\u2013946","journal-title":"In: Proceedings of the AAAI conference on artificial intelligence"},{"key":"6975_CR64","doi-asserted-by":"crossref","unstructured":"Luo W, Liu W, Lian D, Gao S (2021b) Future frame prediction network for video anomaly detection. IEEE Trans Pattern Anal Mach Intell, 44(11):7505\u20137520,","DOI":"10.1109\/TPAMI.2021.3129349"},{"key":"6975_CR65","doi-asserted-by":"crossref","unstructured":"Liu Y, Liu J, Lin J, Zhao M, Song L (2022b) Appearance-motion united auto-encoder framework for video anomaly detection. IEEE Trans Circ Syst II: Express Briefs, 69(5):2498\u20132502,","DOI":"10.1109\/TCSII.2022.3161049"},{"key":"6975_CR66","doi-asserted-by":"crossref","unstructured":"Zhao M, Zeng X, Liu Y, Liu J, Li D, Hu X, Pang C (2022) Lgn-net: Local-global normality network for video anomaly detection. arXiv:2211.07454,","DOI":"10.2139\/ssrn.4339920"},{"key":"6975_CR67","doi-asserted-by":"crossref","unstructured":"Yang Z, Wu P, Liu J, Liu X (2022) Dynamic local aggregation network with adaptive clusterer for anomaly detection. In: European Conference on Computer Vision, pp 404\u2013421. Springer,","DOI":"10.1007\/978-3-031-19772-7_24"},{"issue":"2","key":"6975_CR68","first-page":"963","volume":"33","author":"L Yue","year":"2022","unstructured":"Yue L, Cao C, Zhang Y, Zhang Y (2022) Learnable locality-sensitive hashing for video anomaly detection. IEEE Trans Circuits Syst Video Technol 33(2):963\u2013976","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"6975_CR69","doi-asserted-by":"crossref","unstructured":"Wang Y, Liu T, Zhou J, Guan J (2023a) Video anomaly detection based on spatio-temporal relationships among objects. Neurocomputing, 532:141\u2013151,","DOI":"10.1016\/j.neucom.2023.02.027"},{"key":"6975_CR70","doi-asserted-by":"crossref","unstructured":"Wang J, Jia D, Huang Z, Zhang M, Ren X (2023b) Normal spatio-temporal information enhance for unsupervised video anomaly detection. Neural Process Lett, 55(8):10727\u201310745,","DOI":"10.1007\/s11063-023-11347-5"},{"key":"6975_CR71","doi-asserted-by":"crossref","unstructured":"Hirschorn O, Avidan S (2023) Normalizing flows for human pose anomaly detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 13545\u201313554,","DOI":"10.1109\/ICCV51070.2023.01246"},{"key":"6975_CR72","doi-asserted-by":"crossref","unstructured":"Singh A, Jones M\u00a0J, Learned-Miller E\u00a0G (2023) Eval: Explainable video anomaly localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 18717\u201318726,","DOI":"10.1109\/CVPR52729.2023.01795"},{"key":"6975_CR73","doi-asserted-by":"crossref","unstructured":"Kommanduri R, Ghorai M (2024) Dast-net: Dense visual attention augmented spatio-temporal network for unsupervised video anomaly detection. Neurocomputing 579:127444","DOI":"10.1016\/j.neucom.2024.127444"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06975-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06975-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06975-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T08:06:29Z","timestamp":1764144389000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06975-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":73,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["6975"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06975-4","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"13 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"We comply with ethical and informed consent for the data used.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and Informed Consent for Data Used"}}],"article-number":"1086"}}