From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices.
Mehrtash Tafazzoli HarandiMathieu SalzmannRichard I. HartleyPublished in: ECCV (2) (2014)
Keyphrases
- dimensionality reduction
- symmetric positive definite
- low dimensional
- riemannian manifolds
- spd matrices
- manifold learning
- geometric structure
- euclidean space
- geodesic distance
- high dimensional
- lie group
- euclidean geometry
- parameter space
- feature space
- distribution function
- positive definite
- higher dimensional
- diffusion tensor
- input space
- fisher information
- pattern recognition
- feature extraction