Multi-class binary symbol classification requires the use of rich descriptors and robust classifiers. Shape representation is a difficult task because of several symbol distortions...
This contribution proposes a compositionality architecture for visual object categorization, i.e., learning and recognizing multiple visual object classes in unsegmented, cluttered...
Recent studies have argued that natural vision systems perform classification by utilizing different mechanisms depending on the visual input. In this paper we present a hybrid, ...
— In this paper, we investigate the problem of 3D object categorization of objects typically present in kitchen environments, from data acquired using a composite sensor. Our fra...
Zoltan Csaba Marton, Radu Bogdan Rusu, Dominik Jai...
Weakly supervised discovery of common visual structure in highly variable, cluttered images is a key problem in recognition. We address this problem using deformable part-based mo...