In this paper, we present a method for robustly extracting the silhouette form of the participant within an interactive environment. The approach overcomes the inherent problems as...
We investigate a method using support vector machines (SVMs) with walk-based graph kernels for high-level feature extraction from images. In this method, each image is first segme...
One problem of data-driven answer extraction in open-domain factoid question answering is that the class distribution of labeled training data is fairly imbalanced. This imbalance...
Michael Wiegand, Jochen L. Leidner, Dietrich Klako...
Recent research has demonstrated the strong performance of hidden Markov models applied to information extraction--the task of populating database slots with corresponding phrases...
In this paper we address the problem of discovering word semantic similarities via statistical processing of text corpora. We propose a knowledge-poor method that exploits the sen...
Aristomenis Thanopoulos, Nikos Fakotakis, George K...