Large margin relative distance learning for person re‐identification

Large margin relative distance learning for person re‐identification

Distance metric learning has achieved great success in person re‐identification. Most existing methods that learn metrics from pairwise constraints suffer the problem of imbalanced data. In this study, the authors present a large margin relative distance learning (LMRDL) method which learns the metr...

Full description

Bibliographic Details
Main Authors: Husheng Dong, Shengrong Gong, Chunping Liu, Yi Ji, Shan Zhong
Format: Article
Language:English
Published: Wiley 2017-09-01
Series:IET Computer Vision
Subjects:
large margin relative distance learning
person reidentification
distance metric learning
imbalanced data
LMRDL
triplet constraints
Online Access:https://doi.org/10.1049/iet-cvi.2016.0265

Internet

https://doi.org/10.1049/iet-cvi.2016.0265

Similar Items