Abstract | ||
---|---|---|
Person re-identification (Re-ID) is the task of matching a target person across different cameras, which has drawn extensive attention in computer vision and has become an essential component in the video surveillance system. Despite recent remarkable progress, person re-identification methods are either subject to the power of feature representation, or give equal importance to all examples. To mitigate these issues, we introduce a simple, yet effective, Multi-level and Multi-scale Horizontal Pooling Network (MMHPN) for person re-identification. Concretely, our contributions are three-fold:1) we take partial feature representation into account at different pooling scales and different semantic levels so that various partial information is obtained to form a robust descriptor; 2) we introduce a Part Sensitive Loss (PSL) to reduce the effect of easily classified partition to facilitate training of the person re-identification network, 3) we conduct extensive experimental results using the Market-1501, DukeMTMC-reID and CUHK03 datasets and achieve mAP scores of 83.4%, 75.1% and 65.4% respectively on these challenging datasets. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/s11042-020-09427-y | MULTIMEDIA TOOLS AND APPLICATIONS |
Keywords | DocType | Volume |
Multi-level and multi-scale,Horizontal pooling network,Part sensitive loss,Person re-identification | Journal | 79.0 |
Issue | ISSN | Citations |
39-40 | 1380-7501 | 3 |
PageRank | References | Authors |
0.44 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yunzhou Zhang | 1 | 219 | 30.98 |
Shuangwei Liu | 2 | 5 | 1.81 |
Lin Qi | 3 | 3 | 1.45 |
Sonya Coleman | 4 | 16 | 5.59 |
Dermot Kerr | 5 | 50 | 13.84 |
Weidong Shi | 6 | 3 | 0.44 |