VIPeR (Viewpoint Invariant Pedestrian Recognition)
Introduced by Gray et al. in Evaluating appearance models for recognition, reacquisition, and tracking
The Viewpoint Invariant Pedestrian Recognition (VIPeR) dataset includes 632 people and two outdoor cameras under different viewpoints and light conditions. Each person has one image per camera and each image has been scaled to be 128×48 pixels. It provides the pose angle of each person as 0° (front), 45°, 90° (right), 135°, and 180° (back).
Source: PaMM: Pose-aware Multi-shot Matching for Improving Person Re-identificationPapers
| Paper | Code | Results | Date | Stars |
|---|
