Multi-Task Learning based Video Anomaly Detection with Attention

TL;DR

This paper introduces a multi-task learning approach for video anomaly detection that combines semantic segmentation, future frame prediction, and attention mechanisms to improve motion and appearance anomaly detection accuracy.

Contribution

The proposed method uniquely integrates complementary proxy tasks and attention mechanisms to enhance motion and object class understanding in video anomaly detection.

Findings

Outperforms state-of-the-art methods in anomaly detection accuracy

Effectively models object class and motion patterns

Uses attention to focus on important motion features

Abstract

Multi-task learning based video anomaly detection methods combine multiple proxy tasks in different branches to detect video anomalies in different situations. Most existing methods either do not combine complementary tasks to effectively cover all motion patterns, or the class of the objects is not explicitly considered. To address the aforementioned shortcomings, we propose a novel multi-task learning based method that combines complementary proxy tasks to better consider the motion and appearance features. We combine the semantic segmentation and future frame prediction tasks in a single branch to learn the object class and consistent motion patterns, and to detect respective anomalies simultaneously. In the second branch, we added several attention mechanisms to detect motion anomalies with attention to object parts, the direction of motion, and the distance of the objects from the camera. Our qualitative results show that the proposed method considers the object class effectively and learns motion with attention to the aforementioned important factors which results in a precise motion modeling and a better motion anomaly detection. Additionally, quantitative results show the superiority of our method compared with state-of-the-art methods.