no code implementations • 8 May 2023 • Xuan Son Nguyen, Shuo Yang
Recently, by applying the theory of gyrogroups and gyrovector spaces that is a powerful framework for studying hyperbolic geometry, some works have attempted to build principled generalizations of Euclidean neural networks on matrix manifolds.
no code implementations • ICCV 2021 • Xuan Son Nguyen
In this paper, we propose a novel method for representation and classification of two-person interactions from 3D skeleton sequences.
no code implementations • CVPR 2019 • Xuan Son Nguyen, Luc Brun, Olivier Lézoray, Sébastien Bougleux
A new type of layer is proposed for the third stage, based on a variant of stochastic gradient descent on Stiefel manifolds.