STAN: Spatio-Temporal Adversarial Networks for Abnormal Event Detection
This addresses abnormal event detection in video surveillance, but it is incremental as it builds on existing adversarial and spatio-temporal techniques.
The paper tackles abnormal event detection by proposing STAN, a method using spatio-temporal adversarial networks to encode normal patterns, achieving competitive performance compared to state-of-the-art methods.
In this paper, we propose a novel abnormal event detection method with spatio-temporal adversarial networks (STAN). We devise a spatio-temporal generator which synthesizes an inter-frame by considering spatio-temporal characteristics with bidirectional ConvLSTM. A proposed spatio-temporal discriminator determines whether an input sequence is real-normal or not with 3D convolutional layers. These two networks are trained in an adversarial way to effectively encode spatio-temporal features of normal patterns. After the learning, the generator and the discriminator can be independently used as detectors, and deviations from the learned normal patterns are detected as abnormalities. Experimental results show that the proposed method achieved competitive performance compared to the state-of-the-art methods. Further, for the interpretation, we visualize the location of abnormal events detected by the proposed networks using a generator loss and discriminator gradients.