Clothes-Changing Video person re-ID
Clothes-Changing Video person re-ID (CCVID) is a dataset constructed from the raw data of a gait recognition dataset, i.e. FVG. The reconstructed CCVID dataset contains 347,833 bounding boxes. The length of each sequence changes from 27 to 410 frames, with an average length of 122. Besides, it also provides fine-grained clothes labels including tops, bottoms, shoes, carrying status, and accessories. For the convenience of evaluation, CCVID re-divides the training and test sets to adapt to clothes-changing re-id. Specifically, 75 identities are reserved for training, and the remaining 151 identities are used for test. In the test set, 834 sequences are used as query set, and the other 1074 sequences form gallery set.
Variants: CCVID
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Person Re-Identification | CAL+DLCR | DLCR: A Generative Data Expansion … | 2024-11-11 |
| Person Re-Identification | 3DInvarReID | Learning Clothing and Pose Invariant … | 2023-08-21 |
| Person Re-Identification | CAL | Clothes-Changing Person Re-identification with RGB … | 2022-04-14 |
Recent papers with results on this dataset: