Abstract | ||
---|---|---|
•We propose to learn global and local attention aware features for person ReID.•Two additional branches are introduced to realize the proposed attention aware feature learning in the training stage, and they are removed in the inference time to keep the same model size and inference speed.•Ablation studies and visualization results are included to help understanding the proposed method.•Significant performance improvements over existing methods are achieved on five widely used benchmarks. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.patcog.2022.108567 | Pattern Recognition |
Keywords | DocType | Volume |
Person re-identification,Attention learning,Multi-task learning | Journal | 126 |
ISSN | Citations | PageRank |
0031-3203 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yifan Chen | 1 | 58 | 19.82 |
Han Wang | 2 | 46 | 10.87 |
Sun Xiaolu | 3 | 0 | 0.34 |
Bin Fan | 4 | 589 | 32.14 |
Tang Chu | 5 | 0 | 0.34 |