— A new approach to the 3D human motion tracking problem is proposed, which combines several particle filters with a physical simulation of a flexible body model. The flexible...
In this paper we present a system that can synthesise novel motion sequences from a database of motion capture examples. This is achieved through learning a statistical model from...
Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the h...