Unconstrained Face Verification and Open-World Person Re-identification via Densely-connected Convolution Neural Network

Donghwuy Ko, Jongmin Yu, Ahmad Sheri, Moongu Jeon

Abstract

Although various methods based on the hand-crafted features and deep learning methods have been developed for various applications in the past few years, distinguishing untrained identities in testing phase still remains a challenging task. To overcome these difficulties, we propose a novel representation learning approach to unconstrained face verification and open-world person re-identification tasks. Our approach aims to reinforce the discriminative power of learned features by assigning the weight to each training sample. We demonstrate the efficiency of the proposed method by testing on datasets which are publicly available. The experimental results for both face verification and person re-identification tasks show that its performance is comparable to state-of-the-art methods based on hand-crafted feature and general convolutional neural network.

Download


Paper Citation


in Harvard Style

Ko D., Yu J., Sheri A. and Jeon M. (2019). Unconstrained Face Verification and Open-World Person Re-identification via Densely-connected Convolution Neural Network.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-354-4, pages 443-449. DOI: 10.5220/0007381104430449


in Bibtex Style

@conference{visapp19,
author={Donghwuy Ko and Jongmin Yu and Ahmad Sheri and Moongu Jeon},
title={Unconstrained Face Verification and Open-World Person Re-identification via Densely-connected Convolution Neural Network},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2019},
pages={443-449},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007381104430449},
isbn={978-989-758-354-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - Unconstrained Face Verification and Open-World Person Re-identification via Densely-connected Convolution Neural Network
SN - 978-989-758-354-4
AU - Ko D.
AU - Yu J.
AU - Sheri A.
AU - Jeon M.
PY - 2019
SP - 443
EP - 449
DO - 10.5220/0007381104430449