Weakly Supervised Video Anomaly Detection via Transformer-Enabled Temporal Relation Learning

Weakly supervised video anomaly detection is a challenging problem due to the lack of refined frame-level labels in training videos. Most prior works typically address it with the multiple instance learning paradigm, which divides a video into multiple snippets and trains a snippet classifier to distinguish anomalies from normal snippets via video-level classification loss. However, these solutions are limited in the insufficient representations. In this paper, we propose a novel weakly supervised temporal relation learning framework for anomaly detection, which efficiently explores the temporal relation between snippets and enhances the discriminative powers of features using only video-level labelled videos. To this end, we design a transformer-enabled feature encoder to convert the input task-agnostic features into discriminative task-specific features by mining the semantic similarity and position relation between snippets. As a result, our model can make a more accurate anomaly detection for current video snippet based on the learned discriminative features. Experimental results indicate that the proposed method is superior to existing state-of-the-art approaches, which demonstrates the effectiveness of our model.