We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
This paper reports the results of an experiment to compare three different selection techniques in a tabletop tangible augmented reality interface. Object selection is an importan...
Julian Looser, Mark Billinghurst, Raphael Grasset,...
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...
Abstract. The performance of classification algorithms in machine learning is affected by the features used to describe the labeled examples presented to the inducers. Therefore,...