Psychologists have proposed that many human-object interaction activities form unique classes of scenes. Recognizing these scenes is important for many social functions. To enable...
Large displays are everywhere. However, the computer mouse remains the most common interaction tool for such displays. We propose a new approach for fingertip interaction with lar...
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...
Color and texture have been widely used in image segmentation; however, their performance is often hindered by scene ambiguities, overlapping objects, or missing parts. In this pa...
A probabilistic method for tracking 3D articulated human figures in monocular image sequences is presented. Within a Bayesian framework, we define a generative model of image appea...
Hedvig Sidenbladh, Michael J. Black, David J. Flee...