Name
Title | ||
|---|---|---|
Learning Biased Distance Metrics With Diversity Regularizer For Person Re-Identification |
Abstract | ||
|---|---|---|
Matching certain person across views, known as person re-identification, has attracted much attention in computer vision community. For this challenging problem, metric learning methods have shown their effectiveness in matching person images. In this paper, a Biased Metric Learning with Diversity Regularizer (BMLDR) method is proposed to promote the performance for person re-identification. The adaptive rule in the method assigns biases to different image pairs when the harder the pairs are, the larger weight they will be. By treating images pairs differently, the BMLDR method can exploit more discriminative information provided by the hard pairs thus can effectively distinguish between pairs. We validated the proposed method on three person re-identification datasets including VIPeR, PRID450S and GRID obtaining comparative performance compared to the state-of-the-art methods. |
Year | Venue | Keywords |
|---|---|---|
2017 | 2017 IEEE VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP) | Person re-identification, metric learning, hard pairs, diversity regularizer |
Field | DocType | Citations |
Computer vision,Computer science,Exploit,Artificial intelligence,Discriminative model,Machine learning,Grid | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lei Hao | 1 | 0 | 0.34 |
| Daiying Wang | 2 | 0 | 0.34 |
| Zhu Yuesheng | 3 | 112 | 39.21 |