Recently, a novel Log-Euclidean Riemannian metric [28] is proposed for statistics on symmetric positive definite (SPD) matrices. Under this metric, distances and Riemannian means ...
Xi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang, ...
Model-based image segmentation requires prior information about the appearance of a structure in the image. Instead of relying on Principal Component Analysis such as in Statistica...
In this paper we present a mixture density based approach to invariant image object recognition. We start our experiments using Gaussian mixture densities within a Bayesian classi...
This paper proposes a new registration algorithm, Covariance Driven Correspondences (CDC), that depends fundamentally on the estimation of uncertainty in point correspondences. Th...
Deep belief nets have been successful in modeling handwritten characters, but it has proved more difficult to apply them to real images. The problem lies in the restricted Boltzma...
Marc'Aurelio Ranzato, Alex Krizhevsky, Geoffrey E....