Title
Distance learning by mining hard and easy negative samples for person re-identification.
Abstract
•We have proposed a Hard and Easy Negative samples mining based Distance learning (HEND) approach for person re-identification.•We have designed a symmetric triplet constraint for the proposed HEND approach.•We have proposed a Projection based HEND (PHEND) approach, which simultaneously learns a projection matrix and a distance metric.•We have conducted extensive experiments in this paper to evaluate our approaches.
Year
DOI
Venue
2019
10.1016/j.patcog.2019.06.007
Pattern Recognition
Keywords
Field
DocType
Distance learning,Symmetric triplet constraint,Negative samples division,Projection matrix,Person re-identification
Pattern recognition,Distance education,Metric (mathematics),Artificial intelligence,Discriminative model,Machine learning,Mathematics
Journal
Volume
Issue
ISSN
95
1
0031-3203
Citations 
PageRank 
References 
3
0.40
0
Authors
6
Name
Order
Citations
PageRank
Xiaoke Zhu1787.77
Xiao-Yuan Jing276955.18
Fan Zhang3206.23
Xinyu Zhang42412.48
Xinge You5144183.00
Xiang Cui611520.63