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

Damith Chamalke Senadeera, Xiaoyun Yang, Dimitrios Kollias, Gregory G. Slabaugh

CVPRW 2024 pp. 4888-4897

doi:10.1109/CVPRW63382.2024.00493 /cvprw/2024/senadeera2024cvprw-cuenet/

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. The source code is available at 1.

PDF CVPRW Semantic Scholar

Cite

Text

Senadeera et al. "CUE-Net: Violence Detection Video Analytics with Spatial Cropping, Enhanced UniformerV2 and Modified Efficient Additive Attention." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024. doi:10.1109/CVPRW63382.2024.00493

Markdown

[Senadeera et al. "CUE-Net: Violence Detection Video Analytics with Spatial Cropping, Enhanced UniformerV2 and Modified Efficient Additive Attention." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024.](https://mlanthology.org/cvprw/2024/senadeera2024cvprw-cuenet/) doi:10.1109/CVPRW63382.2024.00493

BibTeX

@inproceedings{senadeera2024cvprw-cuenet,
  title     = {{CUE-Net: Violence Detection Video Analytics with Spatial Cropping, Enhanced UniformerV2 and Modified Efficient Additive Attention}},
  author    = {Senadeera, Damith Chamalke and Yang, Xiaoyun and Kollias, Dimitrios and Slabaugh, Gregory G.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2024},
  pages     = {4888-4897},
  doi       = {10.1109/CVPRW63382.2024.00493},
  url       = {https://mlanthology.org/cvprw/2024/senadeera2024cvprw-cuenet/}
}