Without a deformation model, monocular 3D shape recovery of deformable surfaces is severly under-constrained. Even when the image information is rich enough, prior knowledge of th...
We develop a method for learning the spatial statistics of optical flow fields from a novel training database. Training flow fields are constructed using range images of natur...
The task of selecting information and rendering it appropriately appears in multiple contexts in summarization. In this paper we present a model that simultaneously optimizes sele...
The changing nature of e-Learning, the Web, and its users that can be observed in the last years results in a need for new approaches and technologies to fully exploit the existing...
We describe how to create with machine learning techniques a generative, videorealistic, speech animation module. A human subject is first recorded using a videocamera as he/she u...