Motion-Aware Feature for Improved Video Anomaly Detection

TL;DR

This paper introduces a motion-aware feature and an attention-based temporal MIL model that significantly enhance video anomaly detection and anomalous action recognition performance.

Contribution

It proposes a novel motion-aware feature and integrates temporal context into MIL with attention, achieving state-of-the-art results.

Findings

Achieves competitive performance with existing methods using motion-aware features.

Combining motion-aware features with MIL improves anomaly detection accuracy.

Outperforms previous approaches on UCF Crime dataset.

Abstract

Motivated by our observation that motion information is the key to good anomaly detection performance in video, we propose a temporal augmented network to learn a motion-aware feature. This feature alone can achieve competitive performance with previous state-of-the-art methods, and when combined with them, can achieve significant performance improvements. Furthermore, we incorporate temporal context into the Multiple Instance Learning (MIL) ranking model by using an attention block. The learned attention weights can help to differentiate between anomalous and normal video segments better. With the proposed motion-aware feature and the temporal MIL ranking model, we outperform previous approaches by a large margin on both anomaly detection and anomalous action recognition tasks in the UCF Crime dataset.