Sciweavers

1270 search results - page 4 / 254
» Dogged Learning for Robots
Sort
View
JMLR
2012
11 years 11 months ago
Domain Adaptation: A Small Sample Statistical Approach
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample d...
Ruslan Salakhutdinov, Sham M. Kakade, Dean P. Fost...
CIDM
2007
IEEE
14 years 2 months ago
Prediction of Abnormal Behaviors for Intelligent Video Surveillance Systems
–The OBSERVER is a video surveillance system that detects and predicts abnormal behaviors aiming at the intelligent surveillance concept. The system acquires color images from a ...
Duarte Duque, Henrique Santos, Paulo Cortez
RAS
2002
67views more  RAS 2002»
13 years 8 months ago
Robotic clicker training
In this paper we want to propose the idea that some techniques used for animal training might be helpful for solving human robot interaction problems in the context of entertainme...
Frédéric Kaplan, Pierre-Yves Oudeyer...
TOG
2002
112views more  TOG 2002»
13 years 8 months ago
Integrated learning for interactive synthetic characters
The ability to learn is a potentially compelling and important quality for interactive synthetic characters. To that end, we describe a practical approach to real-time learning fo...
Bruce Blumberg, Marc Downie, Yuri A. Ivanov, Matt ...
CVPR
2009
IEEE
1084views Computer Vision» more  CVPR 2009»
15 years 3 months ago
Describing Objects by their Attributes
We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar ob...
Ali Farhadi, David A. Forsyth, Derek Hoiem, Ian En...