We present a novel approach to non-rigid structure from motion (NRSFM) from an orthographic video sequence, based on a new interpretation of the problem. Existing approaches assum...
In this paper, we present a novel semisupervised regression algorithm working on multiclass data that may lie on multiple manifolds. Unlike conventional manifold regression algori...
Huan Wang, Shuicheng Yan, Thomas S. Huang, Jianzhu...
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...
Texture classification is a classical yet still active topic in computer vision and pattern recognition. Recently, several new texture classification approaches by modeling textur...
We propose a framework to learn statistical shape models for faces as piecewise linear models. Specifically, our methodology builds upon primitive active shape models(ASM) to hand...