IEICE TRANSACTIONS on Information
Multiple-Shot Person Re-Identification by Pairwise Multiple Instance Learning
Summary :
Learning an appearance model for person re-identification from multiple images is challenging due to the corrupted images caused by occlusion or false detection. Furthermore, different persons may wear similar clothes, making appearance feature less discriminative. In this paper, we first introduce the concept of multiple instance to handle corrupted images. Then a novel pairwise comparison based multiple instance learning framework is proposed to deal with visual ambiguity, by selecting robust features through pairwise comparison. We demonstrate the effectiveness of our method on two public datasets.
- Publication
- IEICE TRANSACTIONS on Information Vol.E96-D No.12 pp.2900-2903
- Publication Date
- 2013/12/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E96.D.2900
- Type of Manuscript
- LETTER
- Category
- Image Recognition, Computer Vision
Authors
Chunxiao LIU
Tsinghua University
Guijin WANG
Tsinghua University
Xinggang LIN
Tsinghua University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Chunxiao LIU, Guijin WANG, Xinggang LIN, "Multiple-Shot Person Re-Identification by Pairwise Multiple Instance Learning" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 12, pp. 2900-2903, December 2013, doi: 10.1587/transinf.E96.D.2900.
Abstract: Learning an appearance model for person re-identification from multiple images is challenging due to the corrupted images caused by occlusion or false detection. Furthermore, different persons may wear similar clothes, making appearance feature less discriminative. In this paper, we first introduce the concept of multiple instance to handle corrupted images. Then a novel pairwise comparison based multiple instance learning framework is proposed to deal with visual ambiguity, by selecting robust features through pairwise comparison. We demonstrate the effectiveness of our method on two public datasets.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.2900/_p
Copy
@ARTICLE{e96-d_12_2900,
author={Chunxiao LIU, Guijin WANG, Xinggang LIN, },
journal={IEICE TRANSACTIONS on Information},
title={Multiple-Shot Person Re-Identification by Pairwise Multiple Instance Learning},
year={2013},
volume={E96-D},
number={12},
pages={2900-2903},
abstract={Learning an appearance model for person re-identification from multiple images is challenging due to the corrupted images caused by occlusion or false detection. Furthermore, different persons may wear similar clothes, making appearance feature less discriminative. In this paper, we first introduce the concept of multiple instance to handle corrupted images. Then a novel pairwise comparison based multiple instance learning framework is proposed to deal with visual ambiguity, by selecting robust features through pairwise comparison. We demonstrate the effectiveness of our method on two public datasets.},
keywords={},
doi={10.1587/transinf.E96.D.2900},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - Multiple-Shot Person Re-Identification by Pairwise Multiple Instance Learning
T2 - IEICE TRANSACTIONS on Information
SP - 2900
EP - 2903
AU - Chunxiao LIU
AU - Guijin WANG
AU - Xinggang LIN
PY - 2013
DO - 10.1587/transinf.E96.D.2900
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2013
AB - Learning an appearance model for person re-identification from multiple images is challenging due to the corrupted images caused by occlusion or false detection. Furthermore, different persons may wear similar clothes, making appearance feature less discriminative. In this paper, we first introduce the concept of multiple instance to handle corrupted images. Then a novel pairwise comparison based multiple instance learning framework is proposed to deal with visual ambiguity, by selecting robust features through pairwise comparison. We demonstrate the effectiveness of our method on two public datasets.
ER -
English
