In this paper we address the problem of classifying vector sets. We motivate and introduce a novel method based on comparisons between corresponding vector subspaces. In particula...
Tae-Kyun Kim, Ognjen Arandjelovic, Roberto Cipolla
Reliable detection of fiducial targets in real-world images is addressed in this paper. We show that even the best existing schemes are fragile when exposed to other than laborator...
We introduce a novel approach to modeling the dynamics of human facial motion induced by the action of speech for the purpose of synthesis. We represent the trajectories of a numbe...
In this paper, we present a novel algorithm for incremental principal component analysis. Based on the LargestEigenvalue-Theory, i.e. the eigenvector associated with the largest ei...
This paper presents a system that can automatically recognize four different static human body postures in video sequences. The considered postures are standing, sitting, squattin...