Sciweavers

949 search results - page 95 / 190
» Relating Imperatives to Action
Sort
View
ICC
2009
IEEE
127views Communications» more  ICC 2009»
14 years 2 months ago
Security Games with Incomplete Information
—We study two-player security games which can be viewed as sequences of nonzero-sum matrix games where at each stage of the iterations the players make imperfect observations of ...
Kien C. Nguyen, Tansu Alpcan, Tamer Basar
FGR
2006
IEEE
156views Biometrics» more  FGR 2006»
14 years 1 months ago
A Realtime Shrug Detector
A realtime system for shrug detection is discussed in this paper. The system is automatically initialized by a face detector based on Ada-boost[14]. After frontal face is localize...
Huazhong Ning, Tony X. Han, Yuxiao Hu, ZhenQiu Zha...
ECML
2004
Springer
14 years 1 months ago
Batch Reinforcement Learning with State Importance
Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....
Lihong Li, Vadim Bulitko, Russell Greiner
MM
2003
ACM
241views Multimedia» more  MM 2003»
14 years 1 months ago
Invariance in motion analysis of videos
In this paper, we propose an approach that retrieves motion of objects from the videos based on the dynamic time warping of view invariant characteristics. The motion is represent...
Cen Rao, Mubarak Shah, Tanveer Fathima Syeda-Mahmo...
ATAL
2010
Springer
13 years 9 months ago
Decision rules and decision markets
We explore settings where a principal must make a decision about which action to take to achieve a desired outcome. The principal elicits the probability of achieving the outcome ...
Abraham Othman, Tuomas Sandholm