{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T02:36:32Z","timestamp":1769567792833,"version":"3.49.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100009614","name":"Petroleum Technology Development Fund","doi-asserted-by":"publisher","award":["2059\/22"],"award-info":[{"award-number":["2059\/22"]}],"id":[{"id":"10.13039\/501100009614","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s00138-025-01765-x","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T07:47:10Z","timestamp":1764316030000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid TokenShift-stochastic transformer for rare event detection in video surveillance"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5057-0261","authenticated-orcid":false,"given":"Yahaya Idris","family":"Abubakar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6332-7854","authenticated-orcid":false,"given":"Mamadou","family":"Dia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5722-4115","authenticated-orcid":false,"given":"Patrick","family":"Siarry","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3442-0578","authenticated-orcid":false,"given":"Alice","family":"Othmani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,28]]},"reference":[{"key":"1765_CR1","doi-asserted-by":"publisher","first-page":"47091","DOI":"10.1109\/ACCESS.2024.3382140","volume":"12","author":"YI Abubakar","year":"2024","unstructured":"Abubakar, Y.I., Othmani, A., Siarry, P., Sabri, A.Q.M.: A systematic review of rare events detection across modalities using machine learning and deep learning. IEEE Access 12, 47091\u201347109 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3382140","journal-title":"IEEE Access"},{"key":"1765_CR2","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"1765_CR3","doi-asserted-by":"publisher","unstructured":"Zhang, H., Hao, Y., Ngo, C.-W.: Token shift transformer for video classification. In: Proceedings of the 29th ACM International Conference on Multimedia. MM \u201921, pp. 917\u2013925. Association for Computing Machinery, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3474085.3475272","DOI":"10.1145\/3474085.3475272"},{"issue":"29","key":"1765_CR4","doi-asserted-by":"publisher","first-page":"42457","DOI":"10.1007\/s11042-022-13496-6","volume":"81","author":"N Aslam","year":"2022","unstructured":"Aslam, N., Kolekar, M.H.: Unsupervised anomalous event detection in videos using spatio-temporal inter-fused autoencoder. Multimedia Tools. Appl. 81(29), 42457\u201342482 (2022). https:\/\/doi.org\/10.1007\/s11042-022-13496-6","journal-title":"Multimedia Tools. Appl."},{"key":"1765_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09406-3","author":"W Ullah","year":"2021","unstructured":"Ullah, W., Ullah, A., Haq, I., Muhammad, K., Sajjad, M., Baik, S.: CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks. Multimedia Tools. Appl. (2021). https:\/\/doi.org\/10.1007\/s11042-020-09406-3","journal-title":"Multimedia Tools. Appl."},{"key":"1765_CR6","unstructured":"Vosta, S., Yow, K.-C.: KianNet: a violence detection model using an attention-based CNN-LSTM structure. IEEE J. Mag. IEEE Xplore"},{"key":"1765_CR7","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)"},{"key":"1765_CR8","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Li, X., He, L., Yang, Y., Cheng, G., Tong, Y., Ma, L., Tao, D.: TransVOD: end-to-end video object detection with spatial-temporal transformers. (2022). arXiv:2201.05047","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"1765_CR9","doi-asserted-by":"publisher","first-page":"123977","DOI":"10.1109\/ACCESS.2021.3109102","volume":"9","author":"H Yuan","year":"2021","unstructured":"Yuan, H., Cai, Z., Zhou, H., Wang, Y., Chen, X.: TransAnomaly: video anomaly detection using video vision transformer. IEEE Access 9, 123977\u2013123986 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3109102","journal-title":"IEEE Access"},{"key":"1765_CR10","doi-asserted-by":"publisher","unstructured":"Weng, W., Zhang, Y., Xiong, Z.: Event-based video reconstruction using transformer. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2543\u20132552 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00256","DOI":"10.1109\/ICCV48922.2021.00256"},{"key":"1765_CR11","doi-asserted-by":"crossref","unstructured":"Schueler, J., Ara\u00fajo, H.M., Balashov, S.N., Borg, J.E.: Transforming a rare event search into a not-so-rare event search in real-time with deep learning-based object detection (2024)","DOI":"10.1103\/PhysRevD.111.072004"},{"issue":"3","key":"1765_CR12","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s10044-025-01515-9","volume":"28","author":"AAU Rakhmonov","year":"2025","unstructured":"Rakhmonov, A.A.U., Varnousefaderani, B.A., Kim, J.: A hybrid unsupervised-weakly supervised method for video anomaly detection. Pattern Anal. Appl. 28(3), 135 (2025). https:\/\/doi.org\/10.1007\/s10044-025-01515-9","journal-title":"Pattern Anal. Appl."},{"key":"1765_CR13","doi-asserted-by":"publisher","unstructured":"Sultani, W., Chen, C., Shah, M.: Real-world anomaly detection in surveillance videos. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6479\u20136488 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00678","DOI":"10.1109\/CVPR.2018.00678"},{"key":"1765_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2024.104108","volume":"100","author":"N Aslam","year":"2024","unstructured":"Aslam, N., Kolekar, M.H.: TransGANomaly: transformer based generative adversarial network for video anomaly detection. J. Vis. Commun. Image Represent. 100, 104108 (2024). https:\/\/doi.org\/10.1016\/j.jvcir.2024.104108","journal-title":"J. Vis. Commun. Image Represent."},{"key":"1765_CR15","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 Words: transformers for image recognition at scale (2021) arXiv:2010.11929"},{"issue":"9","key":"1765_CR16","doi-asserted-by":"publisher","first-page":"667","DOI":"10.3390\/insects15090667","volume":"15","author":"K Qiu","year":"2024","unstructured":"Qiu, K., Zhang, Y., Ren, Z., Li, M., Wang, Q., Feng, Y., Chen, F.: SpemNet: a cotton disease and pest identification method based on efficient multi-scale attention and stacking patch embedding. Insects 15(9), 667 (2024). https:\/\/doi.org\/10.3390\/insects15090667","journal-title":"Insects"},{"key":"1765_CR17","doi-asserted-by":"publisher","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C.: Multiscale vision transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6804\u20136815 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00675","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"1765_CR18","doi-asserted-by":"publisher","unstructured":"Atrevi, D.F., Vivet, D., Emile, B.: Rare events detection and localization in crowded scenes based on flow signature. In: 2019 Ninth International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 1\u20136 (2019). https:\/\/doi.org\/10.1109\/IPTA.2019.8936073","DOI":"10.1109\/IPTA.2019.8936073"},{"key":"1765_CR19","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2021.715320","author":"J He","year":"2021","unstructured":"He, J., Cheng, M.X.: Weighting methods for rare event identification from imbalanced datasets. Front. Big Data (2021). https:\/\/doi.org\/10.3389\/fdata.2021.715320","journal-title":"Front. Big Data"},{"key":"1765_CR20","unstructured":"Narayanan, S., Maple, C., Hooper, M.: A point process model for rare event detection (2022). arXiv:2209.04792"},{"key":"1765_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103598","volume":"87","author":"N Aslam","year":"2022","unstructured":"Aslam, N., Rai, P.K., Kolekar, M.H.: A3N: attention-based adversarial autoencoder network for detecting anomalies in video sequence. J. Vis. Commun. Image Represent. 87, 103598 (2022). https:\/\/doi.org\/10.1016\/j.jvcir.2022.103598","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"4","key":"1765_CR22","doi-asserted-by":"publisher","first-page":"77","DOI":"10.31185\/wjcms.188","volume":"2","author":"SH Hendi","year":"2023","unstructured":"Hendi, S.H., Taher, H.B., Hussein, K.Q.: Automated video events detection and classification using CNN-GRU model. Wasit J. Comput. Math. Sci. 2(4), 77\u201386 (2023). https:\/\/doi.org\/10.31185\/wjcms.188","journal-title":"Wasit J. Comput. Math. Sci."},{"issue":"5","key":"1765_CR23","doi-asserted-by":"publisher","first-page":"890","DOI":"10.4218\/etrij.2024-0115","volume":"46","author":"AAU Rakhmonov","year":"2024","unstructured":"Rakhmonov, A.A.U., Subramanian, B., Amirian Varnousefaderani, B., Kim, J.: Automated video events detection and classification using CNN-GRU model. ETRI J. 46(5), 890\u2013903 (2024). https:\/\/doi.org\/10.4218\/etrij.2024-0115","journal-title":"ETRI J."},{"issue":"3","key":"1765_CR24","doi-asserted-by":"publisher","first-page":"1729","DOI":"10.1007\/s00371-023-02882-2","volume":"40","author":"N Aslam","year":"2024","unstructured":"Aslam, N., Kolekar, M.H.: DeMAAE: deep multiplicative attention-based autoencoder for identification of peculiarities in video sequences. Vis. Comput. 40(3), 1729\u20131743 (2024). https:\/\/doi.org\/10.1007\/s00371-023-02882-2","journal-title":"Vis. Comput."},{"issue":"19","key":"1765_CR25","doi-asserted-by":"publisher","first-page":"20867","DOI":"10.1609\/aaai.v39i19.34300","volume":"39","author":"G Tertytchny","year":"2025","unstructured":"Tertytchny, G., Stavrinides, G.L., Michael, M.K.: Rare event detection in imbalanced multi-class datasets using an optimal MIP-based ensemble weighting approach. Proc. AAAI Conf. Artif. Intell. 39(19), 20867\u201320875 (2025). https:\/\/doi.org\/10.1609\/aaai.v39i19.34300","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"1765_CR26","doi-asserted-by":"publisher","unstructured":"Dia, M., Khodabandelou, G., Othmani, A.: A novel stochastic transformer-based approach for post-traumatic stress disorder detection using audio recording of clinical interviews. 2023 IEEE 36th IEEE Symposium on Computer-Based Medical Systems (CBMS) (2023). https:\/\/doi.org\/10.1109\/CBMS58004.2023.00303","DOI":"10.1109\/CBMS58004.2023.00303"},{"key":"1765_CR27","unstructured":"Panousis, K., Chatzis, S., Alexos, A., Theodoridis, S.: Local competition and stochasticity for adversarial robustness in deep learning. In: Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, pp. 3862\u20133870. PMLR (2021)"},{"key":"1765_CR28","unstructured":"Srivastava, R.K., Masci, J., Kazerounian, S., Gomez, F., Schmidhuber, J.: Compete to compute. In: Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2. NIPS\u201913, vol. 2, pp. 2310\u20132318. Curran Associates Inc., Red Hook, NY, USA (2013)"},{"key":"1765_CR29","unstructured":"Liu, Z., Xu, Z., Jin, J., Shen, Z., Darrell, T.: Dropout reduces underfitting. In: Proceedings of the 40th International Conference on Machine Learning, pp. 22233\u201322248. PMLR (2023)"},{"key":"1765_CR30","unstructured":"Wang, Y., Zheng, S., Cao, B., Wei, Q., Zeng, W., Jin, Q., Lu, Z.: Scaling large motion models with million-level human motions (2025). arXiv:2410.03311"},{"key":"1765_CR31","doi-asserted-by":"publisher","unstructured":"Bermejo Nievas, E., Deniz Suarez, O., Bueno Garc\u00eda, G., Sukthankar, R.: violence detection in video using computer vision techniques. In: Real, P., Diaz-Pernil, D., Molina-Abril, H., Berciano, A., Kropatsch, W. (eds.) Computer Analysis of Images And Patterns, pp. 332\u2013339. Springer, Berlin, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-23678-5_39","DOI":"10.1007\/978-3-642-23678-5_39"},{"key":"1765_CR32","doi-asserted-by":"publisher","unstructured":"Vu, D.-Q., Nguyen, T.H., Nguyen, M., Nguyen, B.Y., Phung, T.-N., Thu, T.P.T.: TNUE-Fight detection: a new challenge benchmark for\u00a0fighting recognition. In: Nghia, P.T., Thai, V.D., Thuy, N.T., Son, L.H., Huynh, V.-N. (eds.) Advances in Information and Communication Technology, pp. 308\u2013314. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-50818-9_34","DOI":"10.1007\/978-3-031-50818-9_34"},{"issue":"2","key":"1765_CR33","doi-asserted-by":"publisher","first-page":"251","DOI":"10.71146\/kjmr270","volume":"2","author":"MQ Khan","year":"2025","unstructured":"Khan, M.Q., Sabir, S.N., Malik, F., Khan, M.: Deep convolutional network for automatic violence detection in surveillance videos using transfer learning. Kashf J. Multidiscip. Res. 2(2), 251\u2013275 (2025). https:\/\/doi.org\/10.71146\/kjmr270","journal-title":"Kashf J. Multidiscip. Res."},{"key":"1765_CR34","doi-asserted-by":"publisher","DOI":"10.34028\/iajit\/22\/5\/14","author":"D Calderon-Vilca","year":"2025","unstructured":"Calderon-Vilca, D., Cuadros-Ramos, K., Valcarcel-Ascencios, S., Aguilar-Alonso, I.: Hybrid CNN xception and long short-term memory model for the detection of interpersonal violence in videos. Int. Arab J. Inf. Technol. (2025). https:\/\/doi.org\/10.34028\/iajit\/22\/5\/14","journal-title":"Int. Arab J. Inf. Technol."},{"issue":"8","key":"1765_CR35","doi-asserted-by":"publisher","first-page":"2811","DOI":"10.3390\/s21082811","volume":"21","author":"W Ullah","year":"2021","unstructured":"Ullah, W., Ullah, A., Hussain, T., Khan, Z.A., Baik, S.W.: An efficient anomaly recognition framework using an attention residual LSTM in surveillance videos. Sensors 21(8), 2811 (2021). https:\/\/doi.org\/10.3390\/s21082811","journal-title":"Sensors"},{"key":"1765_CR36","doi-asserted-by":"publisher","DOI":"10.19101\/IJATEE.2021.875907","author":"ZK Abbas","year":"2022","unstructured":"Abbas, Z.K., Al-Ani, A.A.: Anomaly detection in surveillance videos based on H265 and deep learning. Int. J. Adv. Technol. Eng. Explor. (2022). https:\/\/doi.org\/10.19101\/IJATEE.2021.875907","journal-title":"Int. J. Adv. Technol. Eng. Explor."}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-025-01765-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-025-01765-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-025-01765-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T15:07:45Z","timestamp":1769440065000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-025-01765-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,28]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["1765"],"URL":"https:\/\/doi.org\/10.1007\/s00138-025-01765-x","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,28]]},"assertion":[{"value":"23 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2025","order":6,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":7,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Biography section of authors Professor Patrick Siarry and Dr. Alice Othmani\u2019s updated.","order":8,"name":"change_details","label":"Change Details","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":"Conflict of interest"}}],"article-number":"10"}}