Name
Abstract | ||
|---|---|---|
Given a query image, vehicle Re-Identification is to search the same vehicle in multi-camera scenarios, which are attracting much attention in recent years. However, vehicle ReID severely suffers from the perspective variation problem. For different vehicles with similar color and type which are taken from different perspectives, all visual patterns are misaligned and warped, which is hard for the model to find out the exact discriminative regions. In this paper, we propose part perspective transformation module (PPT) to map the different parts of vehicle into a unified perspective respectively. The PPT disentangles the vehicle features of different perspectives and then aligns them in a fine-grained level. Further, we propose a dynamically batch hard triplet loss to select the common visible regions of the compared vehicles. Our approach helps the model to generate the perspective invariant features and find out the exact distinguishable regions for vehicle ReID. Extensive experiments on three standard vehicle ReID datasets show the effectiveness of our method.
|
Year | DOI | Venue |
|---|---|---|
2020 | 10.1145/3394171.3413573 | MM '20: The 28th ACM International Conference on Multimedia
Seattle
WA
USA
October, 2020 |
DocType | ISBN | Citations |
Conference | 978-1-4503-7988-5 | 1 |
PageRank | References | Authors |
0.36 | 15 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dechao Meng | 1 | 17 | 2.89 |
| Liang Li | 2 | 342 | 24.75 |
| Shuhui Wang | 3 | 596 | 51.45 |
| Xingyu Gao | 4 | 106 | 14.95 |
| Zheng-Jun Zha | 5 | 2822 | 152.79 |
| Qingming Huang | 6 | 3919 | 267.71 |