We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class a...
Many data mining applications have a large amount of data but labeling data is often difficult, expensive, or time consuming, as it requires human experts for annotation. Semi-supe...
In multi-agent planning environments, action models for each agent must be given as input. However, creating such action models by hand is difficult and time-consuming, because i...
This study reports the findings of a usability test conducted to examine users' interaction with two different learning object metadata-driven search result interfaces. The f...
Programming a humanoid robot to walk is a challenging problem in robotics. Traditional approaches rely heavily on prior knowledge of the robot's physical parameters to devise...
Rawichote Chalodhorn, David B. Grimes, Keith Groch...