SCITEPRESS (original) (raw)
Paper
VMRFANet: View-specific Multi-Receptive Field Attention Network for Person Re-identification
Topics: Industrial Applications of AI; Vision and Perception
Honglong Cai ; Yuedong Fang ; Zhiguan Wang ; Tingchun Yeh and Jinxing Cheng
Affiliation: Suning Commerce R&D Center, U.S.A.
Keyword(s): Person Re-identification, Attention, View Specific, Data Augmentation
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-a rt methods. (More)
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.
Guests can use SciTePress Digital Library without having a SciTePress account. However, guests have limited access to downloading full text versions of papers and no access to special options.
Guests can use SciTePress Digital Library without having a SciTePress account. However, guests have limited access to downloading full text versions of papers and no access to special options.
Guest:Register as new SciTePress user now for free.
Download limit per month - 500 recent papers or 4000 papers more than 2 years old.
SciTePress user: please login.
You are not signed in, therefore limits apply to your IP address 35.245.65.210
In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total
Paper citation in several formats:
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; ISSN 2184-433X, SciTePress, pages 413-420. DOI: 10.5220/0008917004130420
@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},
issn={2184-433X},
}
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
IS - 2184-433X
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
PB - SciTePress