In this paper, we present a generative sketch model for human hair analysis and synthesis. We treat hair images as 2D piecewisely smooth vector (flow) fields, and thus our represe...
Switched linear systems have a long history of interest in the control community, and have attracted considerable attention recently because they are not only practically relevant...
This paper describes how heterogeneous data sources captured in the SignCom project may be used for the analysis and synthesis of French Sign Language (LSF) utterances. The captur...
This paper describes a probabilistic framework for faithful reproduction of dynamic facial expressions on a synthetic face model with MPEG-4 facial animation parameters (FAPs) whil...
In this paper, we present a scalable fully distributed version of a Mobile Backbone Network Topology Synthesis Algorithm (MBN-TSA) for constructing and maintaining a dynamic backb...