Humans can easily recognize complex objects even if values of their attributes are imprecise and often inconsistent. It is not clear how the brain processes uncertain visual inform...
We propose a novel unsupervised learning framework for activity perception. To understand activities in complicated scenes from visual data, we propose a hierarchical Bayesian mod...
AKIRA is an open source framework designed for parallel, asynchronous and distributed computation, on the basis of some general architectural principles which are inspired by modu...
Can creative visualizations of real time energy consumption patterns trigger more ecologically responsible behavior? Media art that displays the real time usage of key resources s...
Automatic evaluation of visual tracking algorithms in the absence of ground truth is a very challenging and important problem. In the context of online appearance modeling, there ...