Adaptive Graph Convolutional Networks for Weakly Supervised Anomaly Detection in Videos
This work addresses video anomaly detection for security and surveillance applications, presenting an incremental improvement by enhancing contextual modeling.
The paper tackles the problem of inadequate video representation in weakly supervised anomaly detection by proposing an adaptive graph convolutional network (WAGCN) to model long-term contextual relationships among video segments, achieving state-of-the-art performance on public datasets like UCF-Crime and ShanghaiTech.
For weakly supervised anomaly detection, most existing work is limited to the problem of inadequate video representation due to the inability of modeling long-term contextual information. To solve this, we propose a novel weakly supervised adaptive graph convolutional network (WAGCN) to model the complex contextual relationship among video segments. By which, we fully consider the influence of other video segments on the current one when generating the anomaly probability score for each segment. Firstly, we combine the temporal consistency as well as feature similarity of video segments to construct a global graph, which makes full use of the association information among spatial-temporal features of anomalous events in videos. Secondly, we propose a graph learning layer in order to break the limitation of setting topology manually, which can extract graph adjacency matrix based on data adaptively and effectively. Extensive experiments on two public datasets (i.e., UCF-Crime dataset and ShanghaiTech dataset) demonstrate the effectiveness of our approach which achieves state-of-the-art performance.