Sciweavers

510 search results - page 8 / 102
» Gradient Estimation Revitalized
Sort
View
UAI
2008
13 years 8 months ago
Improving Gradient Estimation by Incorporating Sensor Data
An efficient policy search algorithm should estimate the local gradient of the objective function, with respect to the policy parameters, from as few trials as possible. Whereas m...
Gregory Lawrence, Stuart J. Russell
JMLR
2006
143views more  JMLR 2006»
13 years 7 months ago
Geometric Variance Reduction in Markov Chains: Application to Value Function and Gradient Estimation
We study a sequential variance reduction technique for Monte Carlo estimation of functionals in Markov Chains. The method is based on designing sequential control variates using s...
Rémi Munos
MVA
2002
177views Computer Vision» more  MVA 2002»
13 years 7 months ago
Global Motion Estimation Based on the Constrained Spatio-temporal Gradient Method in Model-Based Coding
For global motion estimation in model-based coding, this paper proposes a constrained spatio-temporal gradient method using contour information. To overcome the local minimum prob...
Young Wook Sohn, Doo-Hyun Kim, Dong-O Kim, Rae-Hon...
ICIP
2004
IEEE
14 years 9 months ago
Gradient based dominant motion estimation with integral projections for real time video stabilisation
This paper presents a new expression of the relationship between Integral Projections and motion in an image pair. The resulting new multiresolution gradient based approach is use...
Andrew Crawford, Anil C. Kokaram, François ...
ICCV
2007
IEEE
14 years 9 months ago
Non-additive Approach for Omnidirectional Image Gradient Estimation
The way catadioptric images are acquired implies that they present radial distortions. Therefore, classical processing may not be suitable. This statement will be illustrated by c...
Florence Jacquey, Frederic Comby, Olivier Strauss