Abstract. Computational models that attempt to predict when a virtual human should backchannel are often based on the analysis of recordings of face-to-face conversations between h...
The human visual system is able to quickly and robustly infer a wealth of scene information – the scene "gist" – already after 100 milliseconds of image presentation...
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...
Abstract. Over the past several decades, the mouse has gained prominence in the cardiac electrophysiology literature as the animal model of choice. Using computer models of the mou...
We propose a novel display-based game environment using augmented reality technology with small robots. In this environment, the small robots can be augmented by a display image a...