Person Re-Identification Using Additive Distance Constraint With Similar Labels Loss
Despite the promising progress made in recent years, person re-identification (Re-ID) remains a challenging task due to the intra-class variations. Most of the current studies used the traditional Softmax loss for solutions, but its discriminative capability encounters a bottleneck. Therefore, how t...
Main Authors: | Guofa Li, Lisha Huang, Liangwen Tang, Chunli Han, Yaoyu Chen, Heng Xie, Shen Li, Gang Xu |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9195852/ |
Similar Items
-
COS-LDL: Label Distribution Learning by Cosine-Based Distance-Mapping Correlation
by: Heng-Ru Zhang, et al.
Published: (2020-01-01) -
Multi-Label-Based Similarity Learning for Vehicle Re-Identification
by: Saghir Alfasly, et al.
Published: (2019-01-01) -
Similar Supergraph Search Based on Graph Edit Distance
by: Masataka Yamada, et al.
Published: (2021-07-01) -
Distance antimagic labeling of join and corona of two graphs
by: A.K. Handa, et al.
Published: (2017-08-01) -
Distance antimagic labelings of Cartesian product of graphs
by: Nancy Jaseintha Cutinho, et al.
Published: (2020-09-01)