Global Information Guided Video Anomaly Detection

TL;DR

This paper introduces a novel weakly supervised video anomaly detection framework that leverages global pattern cues and spatial reasoning to improve detection accuracy using only video-level labels.

Contribution

The proposed GIG framework effectively mines global cues and applies spatial reasoning, advancing weakly supervised video anomaly detection methods.

Findings

Demonstrates effectiveness on CityScene challenge

Outperforms existing weakly supervised methods

Utilizes global pattern cues for anomaly detection

Abstract

Video anomaly detection (VAD) is currently a challenging task due to the complexity of anomaly as well as the lack of labor-intensive temporal annotations. In this paper, we propose an end-to-end Global Information Guided (GIG) anomaly detection framework for anomaly detection using the video-level annotations (i.e., weak labels). We propose to first mine the global pattern cues by leveraging the weak labels in a GIG module. Then we build a spatial reasoning module to measure the relevance between vectors in spatial domain with the global cue vectors, and select the most related feature vectors for temporal anomaly detection. The experimental results on the CityScene challenge demonstrate the effectiveness of our model.