What Happened 3 Seconds Ago? Inferring the past with Thermal Imaging
Abstract
Inferring past human motion from RGB images is challenging due to the inherent uncertainty of the prediction problem. Thermal images, on the other hand, encode traces of past human-object interactions left in the environment via thermal radiation measurement. Based on this observation, we collect the first RGB-Thermal dataset for human motion analysis, dubbed Thermal-IM. Then we develop a three-stage neural network model for accurate past human pose estimation. Comprehensive experiments show that thermal cues significantly reduce the ambiguities of this task, and the proposed model achieves remarkable performance. The dataset is available at https://github.com/ZitianTang/Thermal-IM.
Cite
Text
Tang et al. "What Happened 3 Seconds Ago? Inferring the past with Thermal Imaging." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.01641Markdown
[Tang et al. "What Happened 3 Seconds Ago? Inferring the past with Thermal Imaging." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/tang2023cvpr-happened/) doi:10.1109/CVPR52729.2023.01641BibTeX
@inproceedings{tang2023cvpr-happened,
title = {{What Happened 3 Seconds Ago? Inferring the past with Thermal Imaging}},
author = {Tang, Zitian and Ye, Wenjie and Ma, Wei-Chiu and Zhao, Hang},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2023},
pages = {17111-17120},
doi = {10.1109/CVPR52729.2023.01641},
url = {https://mlanthology.org/cvpr/2023/tang2023cvpr-happened/}
}