In this paper, linear multilayer ICA (LMICA) is proposed for extracting independent components from quite high-dimensional observed signals such as large-size natural scenes. Ther...
We propose a convex-concave programming approach for the labeled weighted graph matching problem. The convex-concave programming formulation is obtained by rewriting the weighted ...
Mikhail Zaslavskiy, Francis Bach, Jean-Philippe Ve...
In this paper we develop a system for human behaviour recognition in video sequences. Human behaviour is modelled as a stochastic sequence of actions. Actions are described by a f...
Given a still picture, tour into the picture (TIP) generates a walk-through animation of a 3D scene constructed from the picture. In this paper, we generalize TIP to deal with wat...
Jinho Park, Nambin Heo, Sunghee Choi, Sung Yong Sh...
We propose a new scheme for enlarging generalized learning vector quantization (GLVQ) with weighting factors for the input dimensions. The factors allow an appropriate scaling of ...