We introduce novel discriminative learning algorithms for dynamical systems. Models such as Conditional Random Fields or Maximum Entropy Markov Models outperform the generative Hi...
We introduce a novel algorithm for transforming character animation sequences that preserves essential physical properties of the motion. By using the spacetime constraints dynami...
— Obtaining models of dynamic 3D objects is an important part of content generation for computer graphics. Numerous methods have been extended from static scenarios to model dyna...
We present a tool for real-time visualization of motion features in 2D image sequences. The motion is estimated through an eigenvector analysis of the spatiotemporal structure ten...
The ability to analyze and reproduce specific-person facial expression is an important multimedia content service for mobile communication. In this paper, a novel three-layer faci...
Yuehu Liu, Yuanqi Su, Yang Yang, Fengjuan Wang, Ma...