Traditionally, machine learning approaches for information extraction require human annotated data that can be costly and time-consuming to produce. However, in many cases, there ...
We develope a technique to perform e cient and accurate matching to detect the occurences of a template in a scene. The template may describe an object or a textured surface. Repr...
We propose a concept for integrating multiple sensors in real-time robot control. To increase the controller robustness under diverse uncertainties, the robot systematically gener...
Yorck von Collani, Markus Ferch, Jianwei Zhang, Al...
We present a new technique for managing visual clutter caused by overlapping labels in complex information displays. This technique, "label layering", utilizes stereosco...
SUBSEXPL is a system originally developed to visualise reductions, simpliļ¬cations and normalisations in three important calculi of explicit substitutions and has been applied to...
F. L. C. de Moura, A. V. Barbosa, Mauricio Ayala-R...