2527 search results - page 212 / 506 » Discrete optimization in computer vision |
123
click to vote
ICCV
2005
IEEE
15 years 10 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...
149
click to vote
ECCV
2004
Springer
15 years 8 months ago
2004
Springer
Feature point tracking over a video sequence fails when the points go out of the field of view or behind other objects. In this paper, we extend such interrupted tracking by imposi...
162
click to vote
CLOR
2006
15 years 8 months ago
2006
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...
151
click to vote
ACCV
2009
Springer
15 years 7 months ago
2009
Springer
In this paper, we propose an embedding method to seek an optimal low-dimensional manifold describing the intrinsical pose variations and to provide an identity-independent head pos...
122
click to vote
BMVC
2001
15 years 6 months ago
2001
This paper introduces a new method of registering point sets. The registration error is directly minimized using general-purpose non-linear optimization (the Levenberg–Marquardt...