Riemannian manifolds, kernels and learning
I will talk about recent results from a number of people in the 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. Examples that will be considered are the Essential manifold, relevant in structure from motion; 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
Видео Riemannian manifolds, kernels and learning канала Microsoft Research
Видео Riemannian manifolds, kernels and learning канала Microsoft Research
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Manifolds #1 - Introducing ManifoldsWhat is a Manifold? - Mikhail GromovGeometric Deep Learning on Graphs and Manifolds - #NIPS2017The Riemann Hypothesis, ExplainedRiemann geometry -- covariant derivativeFake It Till You Make It: Face Analysis In The Wild Using Synthetic Data AloneCurtis McMullen: Manifolds, topology and dynamicsWebinar: Quantum Computing by a Quantum AnnealerLie theory for the roboticistMy understanding of the Manifold Hypothesis | Machine learningICLR 2021 Keynote - "Geometric Deep Learning: The Erlangen Programme of ML" - M BronsteinWhat is a Manifold? Lesson 1: Point Set Topology and Topological SpacesShort Talk-What is a Manifold-IMysteries of Modern Physics by Sean CarrollAndrea Bernstein: The Trumps, The Kushners and American GreedThe Mystery of 3-Manifolds - William ThurstonTangent spaces and Riemannian manifoldsLecture 1 | Introduction to Riemannian geometry, curvature and Ricci flow | John W. MorganThe Extraordinary Theorems of John Nash - with Cédric Villani