@inproceedings{3c094f0f7bb9420a9a3b08b2ca0d9a87,
title = "Attention-based cross-modality interaction for multispectral pedestrian detection",
abstract = "Multispectral pedestrian detection has attracted extensive attention, as paired RGB-thermal images can provide complementary patterns to deal with illumination changes in realistic scenarios. However, most of the existing deep-learning-based multispectral detectors extract features from RGB and thermal inputs separately, and fuse them by a simple concatenation operation. This fusion strategy is suboptimal, as undifferentiated concatenation for each region and feature channel may hamper the optimal selection of complementary features from different modalities. To address this limitation, in this paper, we propose an attention-based cross-modality interaction (ACI) module, which aims to adaptively highlight and aggregate the discriminative regions and channels of the feature maps from RGB and thermal images. The proposed ACI module is deployed into multiple layers of a two-branch-based deep architecture, to capture the cross-modal interactions from diverse semantic levels, for illumination-invariant pedestrian detection. Experimental results on the public KAIST multispectral pedestrian benchmark show that the proposed method achieves state-of-the-art detection performance. ",
author = "Tianshan Liu and Rui Zhao and Lam, {Kin Man}",
note = "Publisher Copyright: {\textcopyright} COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.; 2021 International Workshop on Advanced Imaging Technology, IWAIT 2021 ; Conference date: 05-01-2021 Through 06-01-2021",
year = "2021",
month = mar,
doi = "10.1117/12.2590661",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Masayuki Nakajima and Jae-Gon Kim and Wen-Nung Lie and Qian Kemao",
booktitle = "International Workshop on Advanced Imaging Technology, IWAIT 2021",
address = "United States",
}