We propose a method to find candidate 2D articulated model configurations by searching for locally optimal configurations under a weak but computationally manageable fitness functi...
In this paper, we introduce a new approach to adaptive coding which utilizes Stochastic Learning-based Weak Estimation (SLWE) techniques to adaptively update the probabilities of t...
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
: Various algorithms have been proposed for the determination of the optimum paths in line networks. Moving in space is a far more complex problem, where research has been scarce. ...
We propose a novel algorithm for uncalibrated photometric stereo. While most of previous methods rely on various assumptions on scene properties, we exploit constraints in lighting...