Sciweavers

122 search results - page 25 / 25
» Nonstationary Covariance Functions for Gaussian Process Regr...
Sort
View
ICCV
2009
IEEE
13 years 3 months ago
Selection and context for action recognition
Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
Dong Han, Liefeng Bo, Cristian Sminchisescu
RSS
2007
176views Robotics» more  RSS 2007»
13 years 7 months ago
Active Policy Learning for Robot Planning and Exploration under Uncertainty
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
Ruben Martinez-Cantin, Nando de Freitas, Arnaud Do...