Table 2.
Shows summarized information about the multi-modal datasets. ‘*’ indicates the dataset is not publicly available.
| Dataset | Year | #ID | #Camera and Location | RGB | Depth | Skeleton |
|---|---|---|---|---|---|---|
| RGBD-ID | 2012 | 79 | 1 (same location but different clothes and poses) | √ | √ | √ |
| BIWI-RGBD-ID | 2014 | 50 | 1 (same location but different days with different clothes and poses) | √ | √ | √ |
| IAS-Lab | 2014 | 11 | 2 (different locations and people wearing different clothes) | √ | √ | √ |
| KinectREID | 2015 | 71 | 1 (same room with different poses) | √ | √ | √ |
| RobotPKU RGBD-ID | 2017 | 90 | 2 (two different rooms with pose variations) | √ | √ | √ |
| SUCVL RGBD-ID * | 2021 | 58 | 3 (three different indoor locations) | √ | √ |