In this paper we introduce a template-based method for recognizing human actions called Action MACH. Our approach is based on a Maximum Average Correlation Height (MACH) filter. A...
Given a finite number of data points sampled from a low-dimensional manifold embedded in a high dimensional space together with the parameter vectors for a subset of the data poin...
We propose a person-dependent, manifold-based approach for modeling and tracking rigid and nonrigid 3D facial deformations from a monocular video sequence. The rigid and nonrigid ...
In our poster presentation at ISMAR’04 [11], we proposed the idea of an AR training solution including capture and 3D replays of subtle movements. The crucial part missing for r...
The XML language is a W3C standard sustained by both the industry and the scientific community. Therefore, the available information annotated in XML keeps and will keep increasing...
Eugen Popovici, Pierre-Francois Marteau, Gildas M&...