The problem of content-based image and video retrieval with textual queries is often posed as that of visual concept classification, where classifiers for a set of predetermined...
We present an approach for simultaneous monocular 3D face pose and facial animation tracking. The pose and facial features are estimated from observed raw brightness shape-free 2D...
MouseLight is a spatially-aware standalone mobile projector with the form factor of a mouse that can be used in combination with digital pens on paper. By interacting with the pro...
This paper deals with estimation of dense optical flow
and ego-motion in a generalized imaging system by exploiting
probabilistic linear subspace constraints on the flow.
We dea...
Richard Roberts (Georgia Institute of Technology),...
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...