Motion-Aware Feature for Improved Video Anomaly Detection

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.

BMVC 2019

References in corpus (1)

• Two-Stream Convolutional Networks for Action Recognition in Videos

Cited by in corpus (5)

• Multiple Instance Learning for Cheating Detection and Localization in Online Examinations
• A Survey on Deep Learning Techniques for Video Anomaly Detection
• Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video
• Global Information Guided Video Anomaly Detection
• Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learning