Person Re-Identification Using Deformable Patch Metric Learning
Abstract
The methodology for finding the same individual in a network of cameras must deal with significant changes in appearance caused by variations in illumination, viewing angle and a person's pose. Re-identification requires solving two fundamental problems: (1) determining a distance measure between features extracted from different cameras that copes with illumination changes (metric learning); and (2) ensuring that matched features refer to the same body part (correspondence). Most metric learning approaches focus on finding a robust distance measure between bounding box images, neglecting the alignment aspects. In this paper, we propose to learn appearance measures for patches that are combined using a spring model for addressing the correspondence problem. We validated our approach on the VIPeR, i-LIDS and CUHK01 datasets achieving new state of the art performance.
Cite
Text
Bak and Carr. "Person Re-Identification Using Deformable Patch Metric Learning." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016. doi:10.1109/WACV.2016.7477590Markdown
[Bak and Carr. "Person Re-Identification Using Deformable Patch Metric Learning." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016.](https://mlanthology.org/wacv/2016/bak2016wacv-person/) doi:10.1109/WACV.2016.7477590BibTeX
@inproceedings{bak2016wacv-person,
title = {{Person Re-Identification Using Deformable Patch Metric Learning}},
author = {Bak, Slawomir and Carr, Peter},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2016},
pages = {1-9},
doi = {10.1109/WACV.2016.7477590},
url = {https://mlanthology.org/wacv/2016/bak2016wacv-person/}
}