Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amount...
We present an algorithm designed for navigating around a performance that was filmed as a “casual” multi-view video collection: real-world footage captured on hand held camer...
Luca Ballan, Gabriel J. Brostow, Jens Puwein, Marc...
We propose and describe a novel video capturing system called Sat-Cam that can observe and record the users’ activity from effective viewpoints to negate the effects of unstead...
Hansung Kim, Itaru Kitahara, Kiyoshi Kogure, Norih...