We introduce an approach to accurately detect and segment partially occluded objects in various viewpoints and scales. Our main contribution is a novel framework for combining obj...
Human activity can be described as a sequence of 3D body postures. The traditional approach to recognition and 3D reconstruction of human activity has been to track motion in 3D, m...
In previous work we have presented a prototype of an assistant system for the blind that can be used for self-localization and interactive object identification of static objects ...
Semantic detection and recognition of objects and events contained in a video stream has to be performed in order to provide content-based annotation and retrieval of videos. This...
Lamberto Ballan, Marco Bertini, Alberto Del Bimbo,...
In this paper a complete OCR methodology for recognizing historical documents, either printed or handwritten without any knowledge of the font, is presented. This methodology cons...