4035 search results - page 577 / 807 » Useless Actions Are Useful |
218
click to vote
CVPR
2008
IEEE
16 years 9 months ago
2008
IEEE
The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely ch...
198
click to vote
ECCV
2008
Springer
16 years 9 months ago
2008
Springer
Over the years, several spatio-temporal interest point detectors have been proposed. While some detectors can only extract a sparse set of scaleinvariant features, others allow for...
168
click to vote
ECCV
2008
Springer
16 years 9 months ago
2008
Springer
Abstract. Multiple elements such as lighting, colors, dialogue, and camera motion contribute to the style of a movie. Among them, camera motion is commonly overlooked yet a crucial...
204
click to vote
ICML
2007
IEEE
16 years 8 months ago
2007
IEEE
This paper introduces a new approach to actionvalue function approximation by learning basis functions from a spectral decomposition of the state-action manifold. This paper exten...
188
click to vote
ICML
2008
IEEE
16 years 8 months ago
2008
IEEE
We consider the task of reinforcement learning in an environment in which rare significant events occur independently of the actions selected by the controlling agent. If these ev...