State of the art on the MSMT17
In this page, the state-of-the-art methods on MSMT17 dataset are summaried.
Reference | MSMT17 | Notes | ||||
rank-1 | rank-5 | rank-10 | rank-20 | mAP | ||
L. Wei et al. Person Transfer GAN to Bridge Domain Gap for Person Re-Identification. In CVPR, 2018. | 47.6 | 65.0 | 71.8 | 78.2 | 23.0 | GoogleNet[1], euclidean distance |
58.0 | 73.6 | 79.4 | 84.5 | 29.7 | PDC[2], euclidean distance | |
61.4 | 76.8 | 81.6 | 85.9 | 34.0 | GLAD[3], euclidean distance |
[1] C. Szegedy et al. Going deeper with convolutions. In CVPR, 2015.
[2] C. Su et al. Pose-driven deep convolutional model for person re-identification. In ICCV, 2017.
[3] L. Wei et al. Glad: Global-local-alignment descriptor for pedestrian retrieval. In ACM MM, 2017.