A seminar with Professor Richard Hartley, Australian National University

Welcome to a seminar at Chalmers with Prof. Richard Hartley, Australian National University.
Time: Tuesday, September 2 at 3 pm

Location: EB-salen, Hörsalsvägen 11

 

Title: Riemannian manifolds, kernels and learning

Abstract

Prof. Hartley will be talking about recent results from a number of people in his group on Riemannian manifolds in computer vision. In many Vision problems Riemannian manifolds come up as a natural model. Data related to a problem can be naturally represented as a point on a Riemannian manifold. This talk will give an intuitive introduction to Riemannian manifolds, and show how they can be applied in many situations.

Manifolds of interest include the manifold of Positive Definite matrices and the Grassman Manifolds, which have a role in object recognition and classification, and the Kendall shape manifold, which represents the shape of 2D objects.

Of particular interest is the question of when one can define positive-definite kernels on Riemannian manifolds. This would allow the application of kernel techniques of SVMs, Kernel FDA, dictionary
learning etc directly on the manifold.

Here is a link to Richard Hartley’s webpage: Richard Hartley