2 papers
cs.CV2022
Bootstrapped Representation Learning for Skeleton-Based Action Recognition
Olivier Moliner, Sangxia Huang, Kalle Åström
In this work, we study self-supervised representation learning for 3D skeleton-based action recognition. We extend Bootstrap Your Own Latent (BYOL) for representation learning on s…
cs.CV2018
Beyond Gröbner Bases: Basis Selection for Minimal Solvers
Viktor Larsson, Magnus Oskarsson, Kalle Åström +3
Many computer vision applications require robust estimation of the underlying geometry, in terms of camera motion and 3D structure of the scene. These robust methods often rely on…