Visual action recognition is an important problem in computer vision. In this paper, we propose a new method to probabilistically model and recognize actions of articulated object...
We equate nonlinear dimensionality reduction (NLDR) to graph embedding with side information about the vertices, and derive a solution to either problem in the form of a kernel-ba...
We show a simple and efficient way for rendering arbitrary views from so-called free-form light fields, employing a convex free form camera surface and a set of arbitrarily orient...
Hartmut Schirmacher, Christian Vogelgsang, Hans-Pe...
We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Prev...
An interactive tool has been developed for visualizing and creating scaled battlefield based scenarios for use in a simulation testbed to develop and test distributed data fusion ...