The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a n...
Abstract. Bag-of-words model (BOW) is inspired by the text classification problem, where a document is represented by an unsorted set of contained words. Analogously, in the objec...
Mehdi Mirza-Mohammadi, Sergio Escalera, Petia Rade...
Edge detection is one of the most studied problems in computer vision, yet it remains a very challenging task. It is difficult since often the decision for an edge cannot be made ...
Support vector machines (SVMs) have proven to be a powerful technique for pattern classification. SVMs map inputs into a high dimensional space and then separate classes with a hy...
William M. Campbell, Joseph P. Campbell, Douglas A...
In this paper we present a framework for semantic scene parsing and object recognition based on dense depth maps. Five viewindependent 3D features that vary with object class are e...