We propose a joint representation and classification framework that achieves the dual goal of finding the most discriminative sparse overcomplete encoding and optimal classifier p...
We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and fo...
—We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the orga...
Thomas Serre, Lior Wolf, Stanley M. Bileschi, Maxi...
In this paper we redefine and generalize the classic k-nearest neighbors (k-NN) voting rule in a Bayesian maximum-a-posteriori (MAP) framework. Therefore, annotated examples are u...
Paolo Piro, Richard Nock, Frank Nielsen, Michel Ba...
We present a novel categorical object detection scheme that uses only local contour-based features. A two-stage, partially supervised learning architecture is proposed: a rudiment...