VMRFANet: View-specific Multi-Receptive Field Attention Network for Person Re-identification

Honglong Cai, Yuedong Fang, Zhiguan Wang, Tingchun Yeh, Jinxing Cheng

2020

Abstract

Person re-identification (re-ID) aims to retrieve the same person across different cameras. In practice, it still remains a challenging task due to background clutter, variations on body poses and view conditions, inaccurate bounding box detection, etc. To tackle these issues, in this paper, we propose a novel multi-receptive field attention (MRFA) module that utilizes filters of various sizes to help network focusing on informative pixels. Besides, we present a view-specific mechanism that guides attention module to handle the variation of view conditions. Moreover, we introduce a Gaussian horizontal random cropping/padding method which further improves the robustness of our proposed network. Comprehensive experiments demonstrate the effectiveness of each component. Our method achieves 95.5% / 88.1% in rank-1 / mAP on Market-1501, 88.9% / 80.0% on DukeMTMC-reID, 81.1% / 78.8% on CUHK03 labeled dataset and 78.9% / 75.3% on CUHK03 detected dataset, outperforming current state-of-the-art methods.

Paper Citation

in Harvard Style

Cai H., Fang Y., Wang Z., Yeh T. and Cheng J. (2020). VMRFANet: View-specific Multi-Receptive Field Attention Network for Person Re-identification. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-395-7, pages 413-420. DOI: 10.5220/0008917004130420

in Bibtex Style

@conference{icaart20,
author={Honglong Cai and Yuedong Fang and Zhiguan Wang and Tingchun Yeh and Jinxing Cheng},
title={VMRFANet: View-specific Multi-Receptive Field Attention Network for Person Re-identification},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2020},
pages={413-420},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008917004130420},
isbn={978-989-758-395-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - VMRFANet: View-specific Multi-Receptive Field Attention Network for Person Re-identification
SN - 978-989-758-395-7
AU - Cai H.
AU - Fang Y.
AU - Wang Z.
AU - Yeh T.
AU - Cheng J.
PY - 2020
SP - 413
EP - 420
DO - 10.5220/0008917004130420