This paper describes the improvement introduced in the Loquendo–Politecnico di Torino (LPT) speaker recognition system submitted to the NIST SRE10 evaluation campaign. This syst...
Many signals of interest are corrupted by faults of an unknown type. We propose an approach that uses Gaussian processes and a general “fault bucket” to capture a priori uncha...
Michael A. Osborne, Roman Garnett, Kevin Swersky, ...
We propose an enhanced window-based approach to local image registration for robust video mosaicing in scenes with arbitrarily moving foreground objects. Unlike other approaches, ...
Andreas Krutz, Michael R. Frater, Matthias Kunter,...
Gradient-based optical flow estimation methods such as LucasKanade method work well for scenes with small displacements but fail when objects move with large displacements. Hierar...
A system for video on multiscopic 3D displays is considered where the data representation consists of multiview video plus scene depth. At most, 3 multiview video signals are bein...