In this paper, we introduce a robust novel approach for detecting objects category in cluttered scenes by generating boosted contextual descriptors of landmarks. In particular, ou...
The objective of this paper is to parse object trajectories in surveillance video against occlusion, interruption, and background clutter. We present a spatio-temporal graph (ST-G...
d at a high abstraction level, and consists in an expectation-driven search starting from symbolic object descriptions and using a version of a distributed blackboard system for re...
Gian Luca Foresti, Vittorio Murino, Carlo S. Regaz...
Model Abstraction from Examples Yakov Keselman, Member, IEEE, and Sven Dickinson, Member, IEEE The recognition community has typically avoided bridging the representational gap bet...
Shape indexing is a way of making rapid associations between features detected in an image and object models that could have produced them. When model databases are large, the use...