Abstract—We present a general scheme for learning sensorimotor tasks which allows rapid on-line learning and generalization of the learned knowledge to unfamiliar objects. The sc...
Enforced hill-climbing is an effective deterministic hillclimbing technique that deals with local optima using breadth-first search (a process called "basin flooding"). ...
Gradient-based numerical optimization of complex engineering designs offers the promise of rapidly producing better designs. However, such methods generally assume that the object...
Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
Recognition of player actions in broadcast sports video is a challenging task due to low resolution of the players in video frames. In this paper, we present a novel method to rec...