Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Abstract. Robust techniques are developed for determining structure from motion in the uncalibrated case. The structure recovery is based on previous work [7] in which it was shown...
Michael J. Brooks, Wojciech Chojnacki, Anton van d...
We propose a fully Bayesian methodology for generalized kernel mixed models (GKMMs), which are extensions of generalized linear mixed models in the feature space induced by a repr...
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pri...
— Ordinal regression is an important type of learning, which has properties of both classification and regression. Here we describe an effective approach to adapt a traditional ...