Person re-identification (Re-ID) aims to match images of the same person across distinct camera views. In this paper, we propose the Space-Time Guided Association Learning (STGAL) for unsupervised Re-ID without ground truth identity nor image correspondence observed during training. By exploiting the spatial-temporal information presented in pedestrian data, our STGAL is able to identify positive and negative image pairs for learning Re-ID feature representations. Experiments on a variety of datasets confirm the effectiveness of our approach, which achieves promising performance when comparing to the state-of-the-art methods.

Paper

Code

Presentation Video

Chih-Wei Wu, Chih-Ting Liu, Wei-Chih Tu, Yu-Chiang Frank Wang, Yu Tsao and Shao-Yi Chien. "Space-Time Guided Association Learning for Unsupervised Person Re-Identification." IEEE International Conference on Image Processing (ICIP), 2020.

Bibtex

@inproceedings{wu2020stgal,
	title={Space-Time Guided Association Learning For Unsupervised Person Re-Identification},
	author={Wu, Chih-Wei and Liu, Chih-Ting and Tu, Wei-Chih and Tsao, Yu and Wang, Yu-Chiang Frank and Chien, Shao-Yi},
	booktitle={2020 IEEE International Conference on Image Processing (ICIP)},
	pages={2261--2265},
	year={2020},
	organization={IEEE}
}