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...
This paper presents a video stabilization algorithm based on the extraction and tracking of Scale Invariant Feature Transform features through video frames. Implementation of SIFT...
Sebastiano Battiato, Giovanni Gallo, Giovanni Pugl...
—This paper proposes a new algorithm for H.264 rate control, and aims at improving coding quality of high motion scenes. Firstly, the motion estimations using all the possible mo...
We seek to extract the three-dimensional motion of articulated objects by passive sensing. We first developed a multi-view system that segments objects from the background before...
We describe a method to segment and depth order motion layers simultaneously in an image sequence. Previous approaches have tended to ignore the depth ordering issue or treat it a...