Tracking 3D people from monocular video is often poorly constrained. To mitigate this problem, prior knowledge should be exploited. In this paper, the Gaussian process spatio-temp...
We present a novel representation of cyclic human locomotion based on a set of spatio-temporal curves of tracked points on the surface of a person. We start by extracting a set of...
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...
We advocate the use of Scaled Gaussian Process Latent Variable Models (SGPLVM) to learn prior models of 3D human pose for 3D people tracking. The SGPLVM simultaneously optimizes a...
Raquel Urtasun, David J. Fleet, Aaron Hertzmann, P...
A challenge for 3D motion capture by monocular vision is 3D-2D projection ambiguities that may bring incorrect poses during tracking. In this paper, we propose improving 3D motion ...