This paper addresses one of the fundamental problems encountered in performance prediction for object recognition. In particular we address the problems related to estimation of s...
We propose a new method for automated large scale gathering of Web images relevant to specified concepts. Our main goal is to build a knowledge base associated with as many conce...
We demonstrate our airwriting interface for mobile handsfree text entry. The interface enables a user to input text into a computer by writing in the air like on an imaginary blac...
In this paper, a new learning framework?probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. In the learning stage, the pro...
— In this paper we build an imitation learning algorithm for a humanoid robot on top of a general world model provided by learned object affordances. We consider that the robot h...