High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
We consider the problem of automatically generating viewpoint motions for a virtual camera tracking a moving target. Given the target's trajectory, we plan the motion of a ca...
This paper demonstrates a new visual motion estimation technique that is able to recover high degree-of-freedom articulated human body configurations in complex video sequences. W...
In television shows, we are familiar with the sound of artificial laughter, the so called “canned laughter” or “laugh track”. It generally has an enhancing effect on the v...
As a case study of a particular control methodology and as a practical contribution in the area of underwater vehicle control, we consider the problem of stabilizing an underwater...