From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices.
Mehrtash Tafazzoli HarandiMathieu SalzmannRichard I. HartleyPublished in: CoRR (2014)
Keyphrases
- dimensionality reduction
- manifold learning
- low dimensional
- riemannian manifolds
- geodesic distance
- geometric structure
- euclidean space
- symmetric positive definite
- spd matrices
- high dimensional
- lie group
- principal component analysis
- euclidean geometry
- high dimensional data
- feature space
- euclidean distance
- dimension reduction
- sparse representation
- higher dimensional
- semi supervised
- feature selection
- anisotropic diffusion
- distribution function
- shortest path
- shape space
- square root
- positive definite
- medical images
- riemannian metric