93 search results - page 1 / 19 » Priors for People Tracking from Small Training Sets |
ICCV
2005
IEEE
14 years 4 months ago
2005
IEEE
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...
CVPR
2006
IEEE
15 years 23 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...
CVPR
2008
IEEE
14 years 5 months ago
2008
IEEE
While low-dimensional image representations have been very popular in computer vision, they suffer from two limitations: (i) they require collecting a large and varied training se...
FGR
2004
IEEE
14 years 2 months ago
2004
IEEE
Tracking a moving person is challenging because a person's appearance in images changes significantly due to articulation, viewpoint changes, and lighting variation across a ...
ICIP
2007
IEEE
15 years 13 days 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...