no code implementations • 5 Jun 2020 • Anton Mallasto, Augusto Gerolin, Hà Quang Minh
As the geometries change by varying the regularization magnitude, we study the limiting cases of vanishing and infinite magnitudes, reconfirming well-known results on the limits of the Sinkhorn divergence.
no code implementations • 29 Sep 2016 • Hà Quang Minh, Marco San Biagio, Loris Bazzani, Vittorio Murino
This paper presents a novel framework for visual object recognition using infinite-dimensional covariance operators of input features in the paradigm of kernel methods on infinite-dimensional Riemannian manifolds.