Existing video anomaly detection methods and datasets suffer from restricted anomaly categories containing single-source (CCTV) videos recorded in controlled environment …
Video anomaly event detection (VAED) is one of the key technologies in computer vision for smart surveillance systems. With the advent of deep learning, contemporary advances in …
Anomaly detection in surveillance videos, as a special case of video-based action recognition, has been of increasing interest in multimedia community and public security …
W Tan, Q Yao, J Liu - Proceedings of the IEEE/CVF Winter …, 2024 - openaccess.thecvf.com
Current weakly supervised video anomaly detection algorithms mostly use multiple instance learning (MIL) or their varieties. Almost all recent approaches focus on how to select the …
G Yu, S Wang, Z Cai, X Liu, E Zhu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Although great progress has been sparked in video anomaly detection (VAD) by deep neural networks (DNNs), existing solutions still fall short in two aspects: 1) The extraction of …
S Yi, Z Fan, D Wu - Image and Vision Computing, 2022 - Elsevier
Video anomaly detection refers to detecting anomalies automatically without manual labor, which is of great significance to intelligent security. With the emergence of weakly …
C Zhang, G Li, Q Xu, X Zhang, L Su… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Although various weakly supervised anomaly detection methods have been proposed in recent years, generalization of anomaly detection is still not well-explored. Existing weakly …
S AlMarri, MZ Zaheer… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Weakly-supervised video anomaly detection (WS-VAD) is a challenging task because coarse video-level annotations are insufficient to train fine-grained (segment or frame-level) …
K Doshi, Y Yilmaz - Proceedings of the IEEE/CVF Winter …, 2022 - openaccess.thecvf.com
Anomaly detection in videos has been attracting an increasing amount of attention. Despite the competitive performance of recent methods on benchmark datasets, they typically lack …