Cross-Modality Interactive Attention Network for Multispectral Pedestrian Detection

Created by Lu Zhang, Institute of Automation, Chinese Academy of Science.

Introduction

We propose a novel single-shot multispectral pedestrian detector, called CIAN, that utilizes the cross-modality (e.g., color, and long-wavelength infrared) information in an adaptive way. For more details, please refer to our paper.

Updated: Evaluation results are now updated on the improved testing annotations provided by Liu et al. for a reliable comparison.

Downloads

Detection results are available through [Google Drive] and [BaiduYun]. If you have any problem, please feel free to contact me.

Citing the paper

Please cite our paper in your publications if it helps your research:

@article{zhang2019cross,
  title={Cross-modality interactive attention network for multispectral pedestrian detection},
  author={Zhang, Lu and Liu, Zhiyong and Zhang, Shifeng and Yang, Xu and Qiao, Hong and Huang, Kaizhu and Hussain, Amir},
  journal={Information Fusion},
  volume={50},
  pages={20--29},
  year={2019},
  publisher={Elsevier}
}