Sciweavers

790 search results - page 144 / 158
» Subexponential Parameterized Algorithms
Sort
View
IVC
2007
187views more  IVC 2007»
14 years 12 months ago
Non-rigid structure from motion using ranklet-based tracking and non-linear optimization
In this paper, we address the problem of estimating the 3D structure and motion of a deformable object given a set of image features tracked automatically throughout a video seque...
Alessio Del Bue, Fabrizio Smeraldi, Lourdes de Aga...
JCB
2002
70views more  JCB 2002»
14 years 11 months ago
Strong Feature Sets from Small Samples
For small samples, classi er design algorithms typically suffer from over tting. Given a set of features, a classi er must be designed and its error estimated. For small samples, ...
Seungchan Kim, Edward R. Dougherty, Junior Barrera...
JMLR
2010
148views more  JMLR 2010»
14 years 6 months ago
A Generalized Path Integral Control Approach to Reinforcement Learning
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
Evangelos Theodorou, Jonas Buchli, Stefan Schaal
ICCV
1999
IEEE
16 years 1 months ago
Capturing Articulated Human Hand Motion: A Divide-and-Conquer Approach
The use of human hand as a natural interface device serves as a motivating force for research in the modeling, analyzing and capturing of the motion of articulated hand. Model-bas...
Ying Wu, Thomas S. Huang
GECCO
2010
Springer
230views Optimization» more  GECCO 2010»
15 years 4 months ago
Exponential natural evolution strategies
The family of natural evolution strategies (NES) offers a principled approach to real-valued evolutionary optimization by following the natural gradient of the expected fitness....
Tobias Glasmachers, Tom Schaul, Yi Sun, Daan Wiers...