Intermediate fused network with multiple timescales for anomaly detection.

This paper proposes an intermediate fused network with multiple timescales to predict future video segments for video anomaly detection. Video prediction technique for anomaly detection requires to derive an anomaly-distinguishable future frame from normal distributions provided by training data. Then by measuring the difference between generated frames and reference frames, the model can tell which frames represent anomalous events in certain video sequence. In order to synthesize more distinctive future frames, we propose to boost image predictions by integrating several input video segments in multiple timescales. Specifically, the diversity in timescales means the diversity in sampling frequencies of video frames. In addition, we introduce a novel intermediate fusion strategy by concatenating feature maps from intermediate layers to better preserve different characteristics from different timescales. We evaluate the proposed method on some public video surveillance datasets and achieve competitive results with respect to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]