2 papers
cs.CV2026
PRGCN: A Graph Memory Network for Cross-Sequence Pattern Reuse in 3D Human Pose Estimation
Zhuoyang Xie, Yibo Zhao, Hui Huang +2
Monocular 3D human pose estimation remains a fundamentally ill-posed inverse problem due to the inherent depth ambiguity in 2D-to-3D lifting. While contemporary video-based methods…
cs.CV2025
Multiple Information Prompt Learning for Cloth-Changing Person Re-Identification
Shengxun Wei, Zan Gao, Chunjie Ma +3
Cloth-changing person re-identification is a subject closer to the real world, which focuses on solving the problem of person re-identification after pedestrians change clothes. Th…