CUE-Net: Violence Detection Video Analytics with Spatial Cropping, Enhanced UniformerV2 and Modified Efficient Additive Attention

TL;DR

CUE-Net is a new video violence detection architecture that combines spatial cropping, enhanced UniformerV2, and a novel attention mechanism to efficiently identify violent activities in surveillance videos, achieving state-of-the-art results.

Contribution

It introduces a novel Modified Efficient Additive Attention mechanism and integrates it with an enhanced UniformerV2 architecture for improved violence detection.

Findings

Achieves state-of-the-art performance on RWF-2000 and RLVS datasets.

Effectively captures local and global spatiotemporal features.

Reduces computational complexity of self-attention mechanisms.

Abstract

In this paper we introduce CUE-Net, a novel architecture designed for automated violence detection in video surveillance. As surveillance systems become more prevalent due to technological advances and decreasing costs, the challenge of efficiently monitoring vast amounts of video data has intensified. CUE-Net addresses this challenge by combining spatial Cropping with an enhanced version of the UniformerV2 architecture, integrating convolutional and self-attention mechanisms alongside a novel Modified Efficient Additive Attention mechanism (which reduces the quadratic time complexity of self-attention) to effectively and efficiently identify violent activities. This approach aims to overcome traditional challenges such as capturing distant or partially obscured subjects within video frames. By focusing on both local and global spatiotemporal features, CUE-Net achieves state-of-the-art performance on the RWF-2000 and RLVS datasets, surpassing existing methods.