People Re-identification using Deep Convolutional Neural Network

Guanwen Zhang, Jien Kato, Yu Wang, Kenji Mase

2014

Abstract

One key issue for people re-identification is to find good features or representation to bridge the gaps among different appearances of the same people, which is introduced by large variances in view point, illumination and non-rigid deformation. In this paper, we create a deep convolutional neural network (deep CNN) to solve this problem and integrate feature learning and re-identification into one framework. In order to deal with such ranking-like comparison problem, we introduce a linear support vector machine (linear SVM) to replace conventional softmax activation function. Instead of learning cross-entropy loss, we adopt a margin-based loss of pair-wise image to measure the similarity of the comparing pair. Although the proposed model is quite simple, the experimental result shows encouraging performance of our method.

Paper Citation

in Harvard Style

Zhang G., Kato J., Wang Y. and Mase K. (2014). People Re-identification using Deep Convolutional Neural Network . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-009-3, pages 216-223. DOI: 10.5220/0004740302160223

in Bibtex Style

@conference{visapp14,
author={Guanwen Zhang and Jien Kato and Yu Wang and Kenji Mase},
title={People Re-identification using Deep Convolutional Neural Network},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={216-223},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004740302160223},
isbn={978-989-758-009-3},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)
TI - People Re-identification using Deep Convolutional Neural Network
SN - 978-989-758-009-3
AU - Zhang G.
AU - Kato J.
AU - Wang Y.
AU - Mase K.
PY - 2014
SP - 216
EP - 223
DO - 10.5220/0004740302160223