1704 search results - page 187 / 341 » Learning nonlinear dynamic models |
154
Voted
HUMO
2000
Springer
15 years 7 months ago
2000
Springer
We present an approach for recovering articulated body pose from single monocular images using the Specialized Mappings Architecture (SMA), a non-linear supervised learning archit...
106
Voted
ICML
2010
IEEE
15 years 4 months ago
2010
IEEE
Deep learning has been successfully applied to perform non-linear embedding. In this paper, we present supervised embedding techniques that use a deep network to collapse classes....
156
click to vote
EUSFLAT
2009
15 years 1 months ago
2009
The aim of this paper is to propose a new Kalman Filter Recurrent Neural Network (KFRNN) topology and a recursive Levenberg-Marquardt (L-M) algorithm of its learning capable to est...
171
Voted
CVPR
2011
IEEE
14 years 11 months ago
2011
IEEE
In real-world applications, “what you saw” during training is often not “what you get” during deployment: the distribution and even the type and dimensionality of features...
154
click to vote
ACCV
2010
Springer
14 years 10 months ago
2010
Springer
Discriminative approaches for human pose estimation model the functional mapping, or conditional distribution, between image features and 3D pose. Learning such multi-modal models ...