Learning Appearance-motion Normality for Video Anomaly Detection
This addresses the problem of detecting anomalies in videos for computer vision applications, representing an incremental improvement over existing methods.
The paper tackled video anomaly detection by proposing a spatial-temporal memories augmented two-stream auto-encoder framework that learns appearance and motion normality independently and explores their correlations via adversarial learning, achieving AUCs of 98.1% on UCSD Ped2 and 89.8% on CUHK Avenue datasets.
Video anomaly detection is a challenging task in the computer vision community. Most single task-based methods do not consider the independence of unique spatial and temporal patterns, while two-stream structures lack the exploration of the correlations. In this paper, we propose spatial-temporal memories augmented two-stream auto-encoder framework, which learns the appearance normality and motion normality independently and explores the correlations via adversarial learning. Specifically, we first design two proxy tasks to train the two-stream structure to extract appearance and motion features in isolation. Then, the prototypical features are recorded in the corresponding spatial and temporal memory pools. Finally, the encoding-decoding network performs adversarial learning with the discriminator to explore the correlations between spatial and temporal patterns. Experimental results show that our framework outperforms the state-of-the-art methods, achieving AUCs of 98.1% and 89.8% on UCSD Ped2 and CUHK Avenue datasets.