High-speed smooth and accurate visual tracking of objects in arbitrary, unstructured environments is essential for robotics and human motion analysis. However, building a system th...
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Tr...
This paper describes how to improve the reusability of iconic program modules. In iconic programming systems, the most important features for reuse are the customization of a modu...
We present a novel range sensing method that is capable of constructing accurate 3D models of specular objects. Our method utilizes a new range imaging concept called multi-peak r...
: The main idea behind Reconfigurable Object Nets (RONs) is to support the visual specification of controlled rule-based net transformations of place/transition nets (P/T nets). RO...