Most current methods for multi-class object classification and localization work as independent 1-vs-rest classifiers. They decide whether and where an object is visible in an imag...
In order to produce robots which can interact more effectively with humans we propose that it is necessary for their cognitive processes to be grounded in the same perceptual elem...
Abstract. A novel approach to create a general vision system is presented. The proposed method is based on a visual grammar representation which is transformed to a Bayesian networ...
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...
A new algorithm for the design of complex features, to be used in the discriminant saliency approach to object classification, is presented. The algorithm consists of sequential r...