Traditional approaches to Multiple-Instance Learning (MIL) operate under the assumption that the instances of a bag are generated independently, and therefore typically learn an in...
Probabilistic Decision Graphs (PDGs) are a class of graphical models that can naturally encode some context specific independencies that cannot always be efficiently captured by...
Despite significant progress in deformable model fitting over the last decade, the problem of efficient and accurate person-independentface fitting remains a challenging probl...
Robotic systems are usually built as independent agents that collaborate to accomplish a specific task. Analysis of robot path planning consists of route planning and path generati...
We introduce a novel approach to modeling the dynamics of human facial motion induced by the action of speech for the purpose of synthesis. We represent the trajectories of a numbe...