We present a new method for segmenting actions into primitives and classifying them into a hierarchy of action classes. Our scheme learns action classes in an unsupervised manner ...
We propose an approach for non-rigid tracking that represents objects by their set of distribution parameters. Compared to joint histogram representations, a set of parameters suc...
This paper proposes a robust video fingerprinting method based on 2-Dimensional Oriented Principal Component Analysis (2D-OPCA) of affine covariant regions. The goal of video fing...
FingerCode has been shown to be an effective representation to capture both the local and global information in a fingerprint. However, the performance of FingerCode is influenced...
In this paper, we present a novel method for processing double-sided historic handwritten documents using wavelets. The method is specially designed to remove the interfering stro...