Vehicle Re-Identification
Vehicle re-identification is the task of identifying the same vehicle across multiple cameras.
( Image credit: A Two-Stream Siamese Neural Network for Vehicle Re-Identification by Using Non-Overlapping Cameras )
Papers
Showing 1–10 of 150 papers
All datasetsVeRi-776VehicleID SmallVehicleID LargeVehicleID MediumVRAI test-devVeRi-Wild SmallVRAI testVeRiVeRi-Wild LargeCityFlowVehicleIDVeRi-Wild Medium
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Recall@k Surrogate loss (ViT-B/16) | Rank-1 | 94.7 | — | Unverified |
| 2 | Recall@k Surrogate loss (ResNet-50) | Rank-1 | 93.8 | — | Unverified |
| 3 | PNP Loss | Rank-1 | 93.2 | — | Unverified |
| 4 | RPTM | Rank-1 | 92.9 | — | Unverified |
| 5 | Smooth-AP | Rank-1 | 91.9 | — | Unverified |
| 6 | ANet | Rank-1 | 80.5 | — | Unverified |
| 7 | vehiclenet | Rank-1 | 79.46 | — | Unverified |
| 8 | MSINet (2.3M w/o RK) | Rank-1 | 77.9 | — | Unverified |
| 9 | CAL | Rank-1 | 75.1 | — | Unverified |
| 10 | QD-DLF | mAP | 68.41 | — | Unverified |