AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 1241 - 1251
• Main Authors: Nguyen, Huy, Nguyen, Kien, Pemasiri, Akila, Liu, Feng, Sridharan, Sridha, Fookes, Clinton
• Format: Conference Proceeding
• Language: English
• Published: IEEE 10.06.2025
• Subjects: aerial-ground person re-identification; Benchmark testing; Cameras; Codes; Computer vision; cross-platform person re-identification; Distance measurement; Drones; Identification of persons; large-scale dataset; multi-stream network; Pattern recognition; Representation learning; Robustness; video-based person re-identification
• ISSN: 1063-6919
• DOI: 10.1109/CVPR52734.2025.00124

We introduce AG-VPReID, a new large-scale dataset for aerial-ground video-based person re-identification (ReID) that comprises 6,632 subjects, 32,321 tracklets and over 9.6 million frames captured by drones (altitudes ranging from 15-120m), CCTV, and wearable cameras. This dataset offers a real-worl...