HYPERPOSE uses hyperbolic kinematic phase-space attention and a Riemannian loss to achieve state-of-the-art 3D pose estimation by preserving skeletal hierarchy and reducing volume distortion.
Hypformer: Exploring efficient hyperbolic transformer fully in hyperbolic space
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation
HYPERPOSE uses hyperbolic kinematic phase-space attention and a Riemannian loss to achieve state-of-the-art 3D pose estimation by preserving skeletal hierarchy and reducing volume distortion.