Kernelized View Adaptive Subspace Learning for Person Re-identification

Qin Zhou, Shibao Zheng, Hang Su, Hua Yang, Yu Wang and Shuang Wu

Abstract

Person re-identification refers to the task of recognizing the same person under different non-overlapping camera views and across different time and places. Many successful methods exploit complex feature representations or sophisticated learners. A recent trend to tackle this problem is to learn a suitable distance metric, the aim of which is to minimize the distance between true matches while maximizing the distance between mismatched pairs. However, most of the existing metric learning algorithms directly take the difference of pairwise features in the original feature space as input. By doing so, they implicitly assume that there exists a projection matrix which can map feature vectors in two different subspaces into an identical subspace where desired feature distribution(features of the same person come closely and faraway otherwise) can be achieved. In this paper, we propose to learn different projection matrices for different camera views, thereby the learned matrices are adaptive to different camera views and a common subspace satisfying the desired feature distribution is more likely to be pursued. To better adapt to the different variations encountered by different views, the kernel trick is adopted to catch more information such that nonlinear transformation is possible. During test phase, the features under different camera views are projected into the learned subspace and a simple nearest neighbor classification is performed. Extensive experiments on four challenging datasets (VIPeR, iLIDS, CAVIAR4REID and ETHZ) demonstrate the effectiveness of the proposed algorithm.

Session

Poster 1

Files

Extended Abstract (PDF, 2M)
Paper (PDF, 5M)

DOI

10.5244/C.29.26
https://dx.doi.org/10.5244/C.29.26

Citation

Bibtex

@inproceedings{BMVC2015_26,
	title={Kernelized View Adaptive Subspace Learning for Person Re-identification},
	author={Qin Zhou and Shibao Zheng and Hang Su and Hua Yang and Yu Wang and Shuang Wu},
	year={2015},
	month={September},
	pages={26.1-26.12},
	articleno={26},
	numpages={12},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.26},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.26}
}