Attribute-based Representations for Accurate and Interpretable Video Anomaly Detection

1 Dec 2022  Β·  Tal Reiss, Yedid Hoshen Β·

Video anomaly detection (VAD) is a challenging computer vision task with many practical applications. As anomalies are inherently ambiguous, it is essential for users to understand the reasoning behind a system's decision in order to determine if the rationale is sound. In this paper, we propose a simple but highly effective method that pushes the boundaries of VAD accuracy and interpretability using attribute-based representations. Our method represents every object by its velocity and pose. The anomaly scores are computed using a density-based approach. Surprisingly, we find that this simple representation is sufficient to achieve state-of-the-art performance in ShanghaiTech, the largest and most complex VAD dataset. Combining our interpretable attribute-based representations with implicit, deep representation yields state-of-the-art performance with a $99.1\%, 93.3\%$, and $85.9\%$ AUROC on Ped2, Avenue, and ShanghaiTech, respectively. Our method is accurate, interpretable, and easy to implement.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Anomaly Detection CUHK Avenue AI-VAD AUC 93.7% # 2
Anomaly Detection ShanghaiTech AI-VAD AUC 85.94% # 2
Abnormal Event Detection In Video UCSD Ped2 AI-VAD AUC 99.1 # 1

Methods


No methods listed for this paper. Add relevant methods here