We develop an algorithm for opponent modeling in large extensive-form games of imperfect information. It works by observing the opponent’s action frequencies and building an opp...
Recent advances in gesture recognition made the problem of controlling a humanoid robot in the most natural possible way an interesting challenge. Learning from Demonstration fie...
In this paper we present the first public key encryption scheme that is structure preserving, i.e., our encryption scheme uses only algebraic operations. In particular it does not...
Jan Camenisch, Kristiyan Haralambiev, Markulf Kohl...
- Large-scale digitisation has led to a number of new possibilities with regard to adaptive and learning based methods in the field of Document Image Analysis and OCR. For ground t...
C. Clausner, Stefan Pletschacher, Apostolos Antona...
We propose a novel approach to understanding
activities from their partial observations monitored through
multiple non-overlapping cameras separated by unknown time
gaps. In our...