119 search results - page 4 / 24 » A novel method for learning policies from constrained motion |
PAMI
2008
13 years 6 months ago
2008
This paper describes methods for recovering time-varying shape and motion of nonrigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talkin...
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
This paper introduces a fully-automated, unsupervised method to recognise sign from subtitles. It does this by using data mining to align correspondences in sections of videos. Bas...
CRV
2011
IEEE
12 years 6 months ago
2011
IEEE
—Motion information is an important cue for a robot to separate foreground moving objects from the static background world. Based on the observation that the motion of the backgr...
NIPS
1993
13 years 7 months ago
1993
While exploring to nd better solutions, an agent performing online reinforcement learning (RL) can perform worse than is acceptable. In some cases, exploration might have unsafe, ...
JAIR
2011
13 years 1 months ago
2011
Markovian processes have long been used to model stochastic environments. Reinforcement learning has emerged as a framework to solve sequential planning and decision-making proble...