In this paper, we develop a general classification framework called Kullback-Leibler Boosting, or KLBoosting. KLBoosting has following properties. First, classification is based o...
Markerless tracking of human pose is a hard yet relevant problem. In this paper, we derive an efficient filtering algorithm for tracking human pose at 4-10 frames per second using...
Varun Ganapathi, Christian Plagemann, Sebastian Th...
A traditional solution of area-based stereo uses some kind of windowed pixel intensity correlation. This approach suffers from discretization artifacts which corrupt the correlat...
We describe an efficient learning algorithm for aligning a symbolic representation of a musical piece with its acoustic counterpart. Our method employs a supervised learning appr...
In this paper, we call the pattern classification problem that consists in assigning a category label to a long audio signal based on its semantic content as Generic Audio Documen...