790 search results - page 1 / 158 » Gaussian Process Dynamical Models for Human Motion |
108
Voted
CVPR
2006
IEEE
16 years 8 days ago
2006
IEEE
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...
81
Voted
PAMI
2008
14 years 10 months ago
2008
We introduce Gaussian process dynamical models (GPDMs) for nonlinear time series analysis, with applications to learning models of human pose and motion from high-dimensional motio...
109
Voted
CVPR
2009
IEEE
2009
IEEE
Switching Gaussian Process Dynamic Models for simultaneous composite motion tracking and recognition
15 years 2 months ago
Traditional dynamical systems used for motion tracking cannot effectively handle high dimensionality of the motion states and composite dynamics. In this paper, to address both is...
115
Voted
ICIP
2007
IEEE
15 years 12 months ago
2007
IEEE
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...
104
Voted
ICCV
2007
IEEE
16 years 6 days ago
2007
IEEE
In this paper, we present a tracking framework for capturing articulated human motions in real-time, without the need for attaching markers onto the subject's body. This is a...