We describe a new approach for phoneme recognition which aims at minimizing the phoneme error rate. Building on structured prediction techniques, we formulate the phoneme recogniz...
Abstract. Popular algorithms for feature matching and model extraction fall into two broad categories, generate-and-test and Hough transform variations. However, both methods suer...
In this paper, we propose classifier ensemble selection for Named Entity Recognition (NER) as a single objective optimization problem. Thereafter, we develop a method based on gen...
Histograms of local appearance descriptors are a popular representation for visual recognition. They are highly discriminant with good resistance to local occlusions and to geomet...
This article presents a method aiming at quantifying the visual similarity between an image and a class model. This kind of problem is recurrent in many applications such as objec...