We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...
Abstract. In recent years there has been growing interest in recognition models using local image features for applications ranging from long range motion matching to object class ...
This paper introduces an approach for handling complex labelling problems driven by local constraints. The purpose is illustrated by two applications: detection of the road networ...
We present a novel approach for establishing multiple-view feature correspondences along an unordered set of images taken from substantially different viewpoints. While recently s...
Vittorio Ferrari, Tinne Tuytelaars, Luc J. Van Goo...
— Background subtraction is a method commonly used to segment objects of interest in image sequences. By comparing new frames to a background model, regions of interest can be fo...