The structural features of XML components are an extra source of information that should be used in a contentoriented retrieval task on this type of documents. This paper explores...
In this work, we develop and evaluate a wide range of feature spaces for deriving Levinstyle verb classifications (Levin, 1993). We perform the classification experiments using Ba...
We propose a novel formulation of stereo matching that considers each pixel as a feature vector. Under this view, matching two or more images can be cast as matching point clouds i...
Viewpoint invariant pedestrian recognition is an important yet under-addressed problem in computer vision. This is likely due to the difficulty in matching two objects with unknown...
In this paper, we propose a method to estimate the 3D human posture from monocular image without using the markers. A 3D human body is expressed by a multi-joint model, and a set ...