We propose a method for estimating the pose of a human body using its approximate 3D volume (visual hull) obtained in real time from synchronized videos. Our method can cope with ...
Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that e...
The Kneed Walker is a physics-based model derived from a planar biomechanical characterization of human locomotion. By controlling torques at the knees, hips and torso, the model ...
The work presented here takes place in the field of computer aided analysis of facial expressions displayed in sign language videos. We use Active Appearance Models to model a fac...
We describe an alternative to standard nonnegative matrix factorisation (NMF) for nonnegative dictionary learning. NMF with the Kullback-Leibler divergence can be seen as maximisa...