In this paper we present an algorithm for performance characterization of symbol localization systems. This algorithm is aimed to be a more “reliable” and “open” solution t...
Mathieu Delalandre, Jean-Yves Ramel, Ernest Valven...
Abstract--In this paper we propose a new multi-view semisupervised learning algorithm called Local Co-Training (LCT). The proposed algorithm employs a set of local models with vect...
In this paper we consider the problem of object parsing,
namely detecting an object and its components by composing
them from image observations. Apart from object localization,
...
The goal of motion segmentation and layer extraction can be viewed as the detection and localization of occluding surfaces. A feature that has been shown to be a particularly stro...