{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T08:08:27Z","timestamp":1772611707646,"version":"3.50.1"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia Grant within Ph.D. Work","doi-asserted-by":"publisher","award":["2021.06275.BD"],"award-info":[{"award-number":["2021.06275.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3557948","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T20:35:43Z","timestamp":1743798943000},"page":"60969-60986","source":"Crossref","is-referenced-by-count":4,"title":["A Unified Approach to Video Anomaly Detection: Advancements in Feature Extraction, Weak Supervision, and Strategies for Class Imbalance"],"prefix":"10.1109","volume":"13","author":[{"given":"Rui Z.","family":"Barbosa","sequence":"first","affiliation":[{"name":"FEUP—Faculty of Engineering, University of Porto, Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4948-550X","authenticated-orcid":false,"given":"Hugo S.","family":"Oliveira","sequence":"additional","affiliation":[{"name":"FEUP—Faculty of Engineering, University of Porto, Porto, Portugal"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3645101"},{"key":"ref2","article-title":"Networking systems for video anomaly detection: A tutorial and survey","author":"Liu","year":"2024","journal-title":"arXiv:2405.10347"},{"key":"ref3","article-title":"Generalized out-of-distribution detection: A survey","author":"Yang","year":"2021","journal-title":"arXiv:2110.11334"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106106"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547868"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3450734"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25489"},{"key":"ref11","article-title":"Overlooked video classification in weakly supervised video anomaly detection","author":"Tan","year":"2022","journal-title":"arXiv:2210.06688"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3350084"},{"key":"ref13","article-title":"Learning prompt-enhanced context features for weakly-supervised video anomaly detection","author":"Pu","year":"2023","journal-title":"arXiv:2306.14451"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350998"},{"key":"ref15","article-title":"Learning spatiotemporal features with 3D convolutional networks","author":"Tran","year":"2014","journal-title":"arXiv:1412.0767"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00133"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803657"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025688"},{"key":"ref21","article-title":"CLAWS: Clustering assisted weakly supervised learning with normalcy suppression for anomalous event detection","author":"Zaigham Zaheer","year":"2020","journal-title":"arXiv:2011.12077"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3117737"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3112814"},{"key":"ref25","article-title":"Clustering aided weakly supervised training to detect anomalous events in surveillance videos","author":"Zaigham Zaheer","year":"2022","journal-title":"arXiv:2203.13704"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746822"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859607"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00269"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00461"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/s23187734"},{"key":"ref32","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"arXiv:1502.03167"},{"key":"ref33","article-title":"Computation-efficient deep learning for computer vision: A survey","author":"Wang","year":"2023","journal-title":"arXiv:2308.13998"},{"key":"ref34","article-title":"Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification","author":"Xie","year":"2017","journal-title":"arXiv:1712.04851"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref37","article-title":"A closer look at spatiotemporal convolutions for action recognition","author":"Tran","year":"2017","journal-title":"arXiv:1711.11248"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref39","first-page":"2000","article-title":"STM: Spatio temporal and motion encoding for action recognition","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Jiang"},{"key":"ref40","article-title":"TSM: Temporal shift module for efficient video understanding","author":"Lin","year":"2018","journal-title":"arXiv:1811.08383"},{"key":"ref41","article-title":"Gate-shift networks for video action recognition","author":"Sudhakaran","year":"2019","journal-title":"arXiv:1912.00381"},{"key":"ref42","article-title":"SlowFast networks for video recognition","author":"Feichtenhofer","year":"2018","journal-title":"arXiv:1812.03982"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref44","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref46","article-title":"Video Swin transformer","author":"Liu","year":"2021","journal-title":"arXiv:2106.13230"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref48","article-title":"MViTv2: Improved multiscale vision transformers for classification and detection","author":"Li","year":"2021","journal-title":"arXiv:2112.01526"},{"key":"ref49","article-title":"Non-local neural networks","author":"Wang","year":"2017","journal-title":"arXiv:1711.07971"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_12"},{"key":"ref53","article-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022","journal-title":"arXiv:2201.04676"},{"key":"ref54","article-title":"An image is worth 16\u00d716 words, what is a video worth?","author":"Sharir","year":"2021","journal-title":"arXiv:2103.13915"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref57","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref58","article-title":"MobileCLIP: Fast image-text models through multi-modal reinforced training","author":"Kumar Anasosalu Vasu","year":"2023","journal-title":"arXiv:2311.17049"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01231"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222289"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00775"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104163"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref64","article-title":"Weakly supervised deep detection networks","author":"Bilen","year":"2015","journal-title":"arXiv:1511.02853"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-18913-5_46"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072863"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS52988.2021.9663810"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859718"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3175092"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506580"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-18913-5_52"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892231"},{"key":"ref76","article-title":"Exploiting completeness and uncertainty of pseudo labels for weakly supervised video anomaly detection","author":"Zhang","year":"2022","journal-title":"arXiv:2212.04090"},{"key":"ref77","article-title":"Dynamic erasing network based on multi-scale temporal features for weakly supervised video anomaly detection","author":"Zhang","year":"2023","journal-title":"arXiv:2312.01764"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3224952"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413686"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCECE54139.2022.9712793"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3216500"},{"key":"ref82","article-title":"Learning weakly supervised audio-visual violence detection in hyperbolic space","author":"Peng","year":"2023","journal-title":"arXiv:2305.18797"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12224623"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00587"},{"key":"ref85","article-title":"Delving into CLIP latent space for video anomaly recognition","author":"Zanella","year":"2023","journal-title":"arXiv:2310.02835"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"ref88","article-title":"GlanceVAD: Exploring glance supervision for label-efficient video anomaly detection","author":"Zhang","year":"2024","journal-title":"arXiv:2403.06154"},{"key":"ref89","article-title":"Towards video anomaly retrieval from video anomaly detection: New benchmarks and model","author":"Wu","year":"2023","journal-title":"arXiv:2307.12545"},{"key":"ref90","article-title":"Towards surveillance video-and-language understanding: New dataset, baselines, and challenges","author":"Yuan","year":"2023","journal-title":"arXiv:2309.13925"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref92","article-title":"Video anomaly detection and explanation via large language models","author":"Lv","year":"2024","journal-title":"arXiv:2401.05702"},{"key":"ref93","article-title":"Open-vocabulary video anomaly detection","author":"Wu","year":"2023","journal-title":"arXiv:2311.07042"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"ref95","article-title":"DataComp: In search of the next generation of multimodal datasets","author":"Gadre","year":"2023","journal-title":"arXiv: 2304.14108"},{"key":"ref96","volume-title":"PyTorch Image Models","author":"Wightman","year":"2019"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10949172.pdf?arnumber=10949172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T04:30:40Z","timestamp":1744345840000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10949172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3557948","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}