Datasets › VRAI
VRAI (Vehicle Re-identification for Aerial Image)
VRAI is a large-scale vehicle ReID dataset for UAV-based intelligent applications. The dataset consists of 137, 613 images of 13, 022 vehicle instances. The images of each vehicle instance are captured by cameras of two DJI consumer UAVs at different locations, with a variety of view angles and flight-altitudes (15m to 80m).
Source: Vehicle Re-identification in Aerial Imagery: Dataset and Approach
Benchmarks archive 2025-07-28
All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Vehicle Re-Identification | VRAI test-dev | Baseline Model MAP 0.78 | — | — | 6 | Compare |
| Vehicle Re-Identification | VRAI test | Baseline Model MAP 0.79 | — | — | 3 | Compare |
Papers archive 2025-07-28
No paper in the archive has a leaderboard row on this dataset; the archive counts 8 papers for it but never published that list.
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- VRAI test
- VRAI test-dev
- VRAI
3 variant names, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections