Generalized video anomaly event detection: Systematic taxonomy and comparison of deep models

Y Liu, D Yang, Y Wang, J Liu, J Liu… - ACM Computing …, 2024 - dl.acm.org
Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance
systems, enabling the temporal or spatial identification of anomalous events within videos …

Look around for anomalies: Weakly-supervised anomaly detection via context-motion relational learning

MA Cho, M Kim, S Hwang, C Park… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Weakly-supervised Video Anomaly Detection is the task of detecting frame-level
anomalies using video-level labeled training data. It is difficult to explore class …

Weakly supervised video anomaly detection via self-guided temporal discriminative transformer

C Huang, C Liu, J Wen, L Wu, Y Xu… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Weakly supervised video anomaly detection is generally formulated as a multiple instance
learning (MIL) problem, where an anomaly detector learns to generate frame-level anomaly …

Anomaly behavior detection analysis in video surveillance: a critical review

S Roka, M Diwakar, P Singh… - Journal of Electronic …, 2023 - spiedigitallibrary.org
Anomaly detection is one of the most researched topics in computer vision and machine
learning. Manual detection of an oddity in a video costs significant time and money, so there …

Hierarchical graph embedded pose regularity learning via spatio-temporal transformer for abnormal behavior detection

C Huang, Y Liu, Z Zhang, C Liu, J Wen, Y Xu… - Proceedings of the 30th …, 2022 - dl.acm.org
Abnormal behavior detection in surveillance video is a fundamental task in modern public
security. Different from typical pixel-based solutions, pose-based approaches leverage low …

Pixel-level anomaly detection via uncertainty-aware prototypical transformer

C Huang, C Liu, Z Zhang, Z Wu, J Wen… - Proceedings of the 30th …, 2022 - dl.acm.org
Pixel-level visual anomaly detection, which aims to recognize the abnormal areas from
images, plays an important role in industrial fault detection and medical diagnosis. However …

M2VAD: multiview multimodality transformer-based weakly supervised video anomaly detection

S Paulraj, S Vairavasundaram - Image and Vision Computing, 2024 - Elsevier
Abstract Video Anomaly Detection (VAD) under a weakly supervised setting involves
operating with limited video-level annotations. The practical significance of this work plays a …

Diffusion-based normality pre-training for weakly supervised video anomaly detection

S Basak, A Gautam - Expert Systems with Applications, 2024 - Elsevier
Weakly supervised video anomaly detection is the task of detecting anomalous frames in
videos where no frame-level labels are provided at training phase. Previous methods …

Deep crowd anomaly detection: state-of-the-art, challenges, and future research directions

MH Sharif, L Jiao, CW Omlin - arxiv preprint arxiv:2210.13927, 2022 - arxiv.org
Crowd anomaly detection is one of the most popular topics in computer vision in the context
of smart cities. A plethora of deep learning methods have been proposed that generally …

Inter-clip Feature Similarity based Weakly Supervised Video Anomaly Detection via Multi-scale Temporal MLP

Y Zhong, R Zhu, G Yan, P Gan… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The major paradigm of weakly supervised video anomaly detection (WSVAD) is treating it as
a multiple instance learning (MIL) problem, with only video-level labels available for training …