ComplexVAD: Detecting Interaction Anomalies in Video

TL;DR

This paper introduces ComplexVAD, a large-scale dataset for complex video anomaly detection involving object interactions, and proposes a novel scene graph-based method that outperforms existing approaches.

Contribution

The paper presents a new dataset, ComplexVAD, and a novel interaction modeling method using scene graphs for detecting complex anomalies in videos.

Findings

The new method outperforms existing video anomaly detection methods on ComplexVAD.

ComplexVAD enables research on complex anomalies involving object interactions.

Baseline scores demonstrate the effectiveness of the proposed approach.

Abstract

Existing video anomaly detection datasets are inadequate for representing complex anomalies that occur due to the interactions between objects. The absence of complex anomalies in previous video anomaly detection datasets affects research by shifting the focus onto simple anomalies. To address this problem, we introduce a new large-scale dataset: ComplexVAD. In addition, we propose a novel method to detect complex anomalies via modeling the interactions between objects using a scene graph with spatio-temporal attributes. With our proposed method and two other state-of-the-art video anomaly detection methods, we obtain baseline scores on ComplexVAD and demonstrate that our new method outperforms existing works.