{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T12:04:07Z","timestamp":1775217847095,"version":"3.50.1"},"reference-count":74,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"vor","delay-in-days":325,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Video surveillance systems are commonly employed to monitor activities and ensure the safety and security of various environments. Anomaly detection in these systems is challenging due to the rarity and high variability of abnormal events. Integrating anomaly detection enables the identification of atypical or suspicious activities. This paper proposes a novel approach for video anomaly detection based on ensemble learning in a weakly supervised setting. The method consists of a two\u2010stage framework. In the first stage, spatiotemporal features are extracted from video data using 3D deep networks, followed by a multi\u2010scale attention module to enhance feature representation. Anomalous events are then identified by analysing discrepancies in probabilistic distributions, incorporating multi\u2010instance learning with a novel term in the loss function. In the second stage, the detection process is refined through ensemble learning strategies to optimise overall performance. The effectiveness of the proposed framework is demonstrated through extensive experiments on five benchmark datasets: UCF\u2010Crime, XD\u2010Violence, ShanghaiTech, CUHK Avenue, and UCSD Ped2. The method achieves frame\u2010level AUC scores of 97.89% on ShanghaiTech, 95.97% on CUHK Avenue, 97.38% on UCSD Ped2, 94.02 on XD\u2010Violence, and 80.86% on UCF\u2010Crime, showing competitive performance and highlighting the potential of ensemble\u2010based weakly supervised methods for video anomaly detection.<\/jats:p>","DOI":"10.1049\/ipr2.70247","type":"journal-article","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T05:40:15Z","timestamp":1763876415000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Video Anomaly Detection With Probabilistic Modelling and Ensemble Learning on Deep Spatiotemporal Features"],"prefix":"10.1049","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3951-1345","authenticated-orcid":false,"given":"Fatemeh","family":"Bameri","sequence":"first","affiliation":[{"name":"Department of Computer Engineering Ferdowsi University of Mashhad  Mashhad Iran"}]},{"given":"Hamid\u2010Reza","family":"Pourreza","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering Ferdowsi University of Mashhad  Mashhad Iran"}]},{"given":"Hamidreza","family":"Mahyar","sequence":"additional","affiliation":[{"name":"Faculty of Engineering McMaster University  Hamilton Canada"}]}],"member":"265","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"crossref","unstructured":"L.Wang Y.Xiong D.Lin andL.Van Gool \u201cUntrimmedNets for Weakly Supervised Action Recognition and Detection \u201d inCVPR(IEEE 2017) 6402\u20136411 https:\/\/doi.org\/10.1109\/CVPR.2017.678.","DOI":"10.1109\/CVPR.2017.678"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530\u2010023\u201001093\u2010y"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227\u2010021\u201004190\u20109"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062192"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104629"},{"key":"e_1_2_11_7_1","doi-asserted-by":"crossref","unstructured":"D.Zhang D.Gatica\u2010Perez S.Bengio andI.McCowan \u201cSemi\u2010Supervised Adapted HMMs for Unusual Event Detection \u201d inCVPR (IEEE 2005) 74\u201381 https:\/\/doi.org\/10.1109\/CVPR.2005.316.","DOI":"10.1109\/CVPR.2005.316"},{"key":"e_1_2_11_8_1","doi-asserted-by":"crossref","unstructured":"J.\u2010C.KimandK.Grauman \u201cObserve Locally Infer Globally: A Space\u2010Time MRF for Detecting Abnormal Activities With Incremental Updates \u201d inCVPR (IEEE 2009) 2921\u20132928 https:\/\/doi.org\/10.1109\/CVPR.2009.5206569.","DOI":"10.1109\/CVPR.2009.5206569"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.937393"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102920"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15143608"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59081-3_23"},{"key":"e_1_2_11_14_1","doi-asserted-by":"crossref","unstructured":"Y.Zhao B.Deng C.Shen Y.Liu H.Lu andX.\u2010S.Hua \u201cSpatio\u2010Temporal AutoEncoder for Video Anomaly Detection \u201d inACM Multimedia (ACM 2017) 1933\u20131941 https:\/\/doi.org\/10.1145\/3123266.3123451.","DOI":"10.1145\/3123266.3123451"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3109102"},{"key":"e_1_2_11_16_1","first-page":"1","article-title":"Self\u2010Supervised Attentive Generative Adversarial Networks for Video Anomaly Detection","author":"Huang C.","year":"2022","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.11.024"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072863"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21227508"},{"key":"e_1_2_11_20_1","doi-asserted-by":"crossref","unstructured":"J.CarreiraandA.Zisserman \u201cQuo Vadis Action Recognition? A New Model and the Kinetics Dataset \u201d inCVPR (IEEE 2017) 4724\u20134733 https:\/\/doi.org\/10.1109\/CVPR.2017.502.","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_2_11_21_1","doi-asserted-by":"crossref","unstructured":"D.Tran L.Bourdev R.Fergus L.Torresani andM.Paluri \u201cLearning Spatiotemporal Features With 3D Convolutional Networks \u201d inCVPR (IEEE 2015) 4489\u20134497 https:\/\/doi.org\/10.1109\/ICCV.2015.510.","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530\u2010022\u201000915\u20109"},{"key":"e_1_2_11_23_1","unstructured":"B.Babenko \u201cMultiple Instance Learning: Algorithms and Applications \u201d (2008):1\u201319 https:\/\/cs.gmu.edu\/~kosecka\/bbabenko_re.pdf."},{"key":"e_1_2_11_24_1","doi-asserted-by":"crossref","unstructured":"V.Mahadevan W.Li V.Bhalodia andN.Vasconcelos \u201cAnomaly Detection in Crowded Scenes \u201d inCVPR (IEEE 2010) 1975\u20131981 https:\/\/doi.org\/10.1109\/CVPR.2010.5539872.","DOI":"10.1109\/CVPR.2010.5539872"},{"key":"e_1_2_11_25_1","doi-asserted-by":"crossref","unstructured":"C.Lu J.Shi andJ.Jia \u201cAbnormal Event Detection at 150 FPS in MATLAB \u201d inCVPR (IEEE 2013) 2720\u20132727 https:\/\/doi.org\/10.1109\/ICCV.2013.338.","DOI":"10.1109\/ICCV.2013.338"},{"key":"e_1_2_11_26_1","doi-asserted-by":"crossref","unstructured":"W.Liu W.Luo D.Lian andS.Gao \u201cFuture Frame Prediction for Anomaly Detection\u2014A New Baseline \u201d inCVPR(IEEE 2018) 6536\u20136545.","DOI":"10.1109\/CVPR.2018.00684"},{"key":"e_1_2_11_27_1","doi-asserted-by":"crossref","unstructured":"P.Wu J.Liu Y.Shi et\u00a0al. \u201cNot Only Look but Also Listen: Learning Multimodal Violence Detection Under Weak Supervision \u201d inECCV(IEEE 2020) 322\u2013339.","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"e_1_2_11_28_1","doi-asserted-by":"crossref","unstructured":"W.Sultani C.Chen andM.Shah \u201cReal\u2010World Anomaly Detection in Surveillance Videos \u201d inCVPR (IEEE 2018) 6479\u20136488 https:\/\/doi.org\/10.1109\/CVPR.2018.00678.","DOI":"10.1109\/CVPR.2018.00678"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3245521"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.01.048"},{"key":"e_1_2_11_31_1","doi-asserted-by":"crossref","unstructured":"S.Wang Y.Zeng Q.Liu C.Zhu E.Zhu andJ.Yin \u201cDetecting Abnormality Without Knowing Normality \u201d inACM Multimedia (ACM 2018) 636\u2013644 https:\/\/doi.org\/10.1145\/3240508.3240615.","DOI":"10.1145\/3240508.3240615"},{"key":"e_1_2_11_32_1","doi-asserted-by":"crossref","unstructured":"M.Ye W.Liu andP.He \u201cVERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision\u2010Language Models \u201d inCVPR(IEEE 2025) 8679\u20138688.","DOI":"10.1109\/CVPR52734.2025.00811"},{"key":"e_1_2_11_33_1","doi-asserted-by":"crossref","unstructured":"L.Zanella W.Menapace M.Mancini Y.Wang andE.Ricci \u201cHarnessing Large Language Models for Training\u2010Free Video Anomaly Detection \u201d inCVPR(IEEE 2024) 18527\u201318536.","DOI":"10.1109\/CVPR52733.2024.01753"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.111"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.06.011"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2637778"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3148392"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933554"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3134410"},{"key":"e_1_2_11_40_1","doi-asserted-by":"crossref","unstructured":"X.Huang C.Zhao J.Yu C.Gao andZ.Wu \u201cMulti\u2010Level Memory\u2010Augmented Appearance\u2010Motion Correspondence Framework for Video Anomaly Detection \u201d inICME(IEEE 2023) 2717\u20132722.","DOI":"10.1109\/ICME55011.2023.00462"},{"key":"e_1_2_11_41_1","doi-asserted-by":"crossref","unstructured":"M.Ye X.Peng W.Gan W.Wu andY.Qiao \u201cAnopcn: Video Anomaly Detection via Deep Predictive Coding Network \u201d inACM MM(ACM 2019) 1805\u20131813.","DOI":"10.1145\/3343031.3350899"},{"key":"e_1_2_11_42_1","doi-asserted-by":"crossref","unstructured":"J.\u2010X.Zhong N.Li W.Kong S.Liu T. H.Li andG.Li \u201cGraph Convolutional Label Noise Cleaner: Train a Plug\u2010and\u2010play Action Classifier for Anomaly Detection \u201d inCVPR(IEEE 2019) 1237\u20131246.","DOI":"10.1109\/CVPR.2019.00133"},{"key":"e_1_2_11_43_1","doi-asserted-by":"crossref","unstructured":"Y.Tian G.Pang Y.Chen R.Singh J. W.Verjans andG.Carneiro \u201cWeakly\u2010Supervised Video Anomaly Detection With Robust Temporal Feature Magnitude Learning\u201d. inCVPR(IEEE 2021) 4975\u20134986.","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3175092"},{"key":"e_1_2_11_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109348"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130030"},{"key":"e_1_2_11_47_1","first-page":"93","article-title":"Sur la Loi de Probabilit\u00e9 de L'\u00e9cart Maximum","volume":"6","author":"Fr\u00e9chet M.","year":"1928","journal-title":"Ann De La Soc Polonaise De Math"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3224952"},{"key":"e_1_2_11_49_1","doi-asserted-by":"crossref","unstructured":"H. K.Joo K.Vo K.Yamazaki andN.Le \u201cCLIP\u2010TSA: Clip\u2010Assisted Temporal Self\u2010Attention for Weakly\u2010Supervised Video Anomaly Detection \u201d inICIP(IEEE 2023) 3230\u20133234.","DOI":"10.1109\/ICIP49359.2023.10222289"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3350084"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296118"},{"key":"e_1_2_11_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3134410"},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3226411"},{"key":"e_1_2_11_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3227044"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.2307\/2348907"},{"key":"e_1_2_11_56_1","first-page":"1","volume-title":"Theoria motus corporum coelestium in sectionibus conicis solem ambientium","author":"Gauss C. F.","year":"1877"},{"key":"e_1_2_11_57_1","doi-asserted-by":"publisher","DOI":"10.1090\/S0002\u20109939\u20101994\u20101195477\u20108"},{"issue":"2","key":"e_1_2_11_58_1","first-page":"115","article-title":"Les Valeurs Extr\u00eames Des Distributions Statistiques","volume":"5","author":"Gumbel E. J.","year":"1935","journal-title":"Annales De L'institut Henri Poincar\u00e9"},{"key":"e_1_2_11_59_1","doi-asserted-by":"publisher","DOI":"10.2307\/2331633"},{"key":"e_1_2_11_60_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177728190"},{"key":"e_1_2_11_61_1","doi-asserted-by":"publisher","DOI":"10.1080\/24709360.2017.1396742"},{"key":"e_1_2_11_62_1","doi-asserted-by":"publisher","DOI":"10.1080\/00949658508810822"},{"key":"e_1_2_11_63_1","doi-asserted-by":"publisher","DOI":"10.1051\/itmconf\/20182300037"},{"key":"e_1_2_11_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"e_1_2_11_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025688"},{"key":"e_1_2_11_66_1","unstructured":"W.Kay J.Carreira K.Simonyan et\u00a0al. \u201cThe Kinetics Human Action Video Dataset \u201d preprint arXiv May 19 2017 https:\/\/doi.org\/10.48550\/arXiv.1705.06950."},{"key":"e_1_2_11_67_1","unstructured":"F.YuandV.Koltun \u201cMulti\u2010Scale Context Aggregation by Dilated Convolutions \u201d preprint arXiv November 23 2015 https:\/\/doi.org\/10.48550\/arXiv.1511.07122."},{"key":"e_1_2_11_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3297114"},{"key":"e_1_2_11_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3023303"},{"key":"e_1_2_11_70_1","first-page":"1","article-title":"Abnormal Event Detection and Localization via Adversarial Event Prediction","volume":"33","author":"Yu J.","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_2_11_71_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.107115"},{"key":"e_1_2_11_72_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042\u2010017\u20105255\u2010z"},{"key":"e_1_2_11_73_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124846"},{"key":"e_1_2_11_74_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128698"},{"key":"e_1_2_11_75_1","doi-asserted-by":"crossref","unstructured":"X.Wang R.Girshick A.Gupta andK.He \u201cNon\u2010local Neural Networks \u201d inICVPR(IEEE 2018) 7794\u20137803.","DOI":"10.1109\/CVPR.2018.00813"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70247","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70247","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T11:26:54Z","timestamp":1775215614000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70247"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":74,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/ipr2.70247"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70247","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-06-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70247"}}