In this paper, we present a novel methodology to detect and recognize objects in cluttered scenes by proposing boosted contextual descriptors of landmarks in a framework of multi-...
Recognizing object classes and their 3D viewpoints is an
important problem in computer vision. Based on a partbased
probabilistic representation [31], we propose a new
3D object...
Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...
A large variety of image features has been invented for detection of objects of a known class. We propose a framework to optimize the discrimination-efficiency tradeoff in integra...
Abstract. In recent years the problem of object recognition has received considerable attention from both the machine learning and computer vision communities. The key challenge of...