The Partial-REID dataset is a uniquely designed partially occluded person re-identification dataset. It uses a new method called Deep Spatial Reconstruction (DSR) for partially occluded person re-identification. It can flexibly process portraits of any size without image alignment and solve the problem of partially occluded person re-identification. Example image: The dataset includes 600 images of 60 people, each with 5 full-body images and 5 occluded images. The images are collected by 6 cameras on a university campus from different perspectives, backgrounds, and different types of occlusions.

Citation

@inproceedings{he2018deep, title={Deep spatial feature reconstruction for partial person re-identification: Alignment-free approach}, author={He, Lingxiao and Liang, Jian and Li, Haiqing and Sun, Zhenan} booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2018} } @inproceedings{he2019foreground, title={Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification}, author={He, Lingxiao and Wang, Yinggang and Liu, Wu and Zhao, He and Sun, Zhenan and Feng, Jiashi} booktitle={IEEE International Conference on Computer Vision (ICCV)}, year={2019} }