Abstract. We propose a probabalistic model of single source multimodal generation and show how algorithms for maximizing mutual information can find the correspondences between com...
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...
We approach the problem of stylistic motion synthesis by learning motion patterns from a highly varied set of motion capture sequences. Each sequence may have a distinct choreogra...
To reduce the production cost of 3D-CG educational contents for e-Learning system and to improve the capability of self-learning system, we developed a new self-learning system ba...