963 search results - page 139 / 193 » Active Learning by Labeling Features |
122
click to vote
CVPR
2008
IEEE
16 years 6 months ago
2008
IEEE
In this paper, we address the pair-activity classification problem, which explores the relationship between two active objects based on their motion information. Our contributions...
158
click to vote
ICCV
2007
IEEE
16 years 6 months ago
2007
IEEE
Many computer vision tasks may be expressed as the problem of learning a mapping between image space and a parameter space. For example, in human body pose estimation, recent rese...
143
click to vote
GAMESEC
2010
15 years 2 months ago
2010
Abstract. Many computer protection tools incorporate learning techniques that build mathematical models to capture the characteristics of system's activity and then check whet...
169
click to vote
ICCV
2005
IEEE
16 years 6 months ago
2005
IEEE
Currently, sharp discontinuities in depth and partial occlusions in multiview imaging systems pose serious challenges for many dense correspondence algorithms. However, it is impo...
126
click to vote
ICML
2002
IEEE
16 years 5 months ago
2002
IEEE
We present several new algorithms for multiagent reinforcement learning. A common feature of these algorithms is a parameterized, structured representation of a policy or value fu...