Pantelis Bouboulis

TL;DR: Equipped with the global directional matching module and the directional appearance model learning module, DDEAL learns static cues from the labeled first frame and dynamically updates cues of the subsequent frames for object segmentation without using online fine-tuning.

TL;DR: The notion of Wirtinger's calculus is extended, for the first time, to include complex RKHSs and use it to derive several realizations of the complex kernel least-mean-square (CKLMS) algorithm, verifying that the CKLMS offers significant performance improvements over several linear and nonlinear algorithms, when dealing with nonlinearities.

TL;DR: Recurrent bivariate fractal interpolation surfaces (RBFISs) generalise the notion of affine fractals in that the iterated system of transformations used to construct such a surface is non-affine, and the resulting limit surface is no longer self-Affine nor self-similar.

TL;DR: Recurrent iterated function systems whose attractors G are graphs of continuous functions f:I→, which interpolate the data are introduced and the fractal dimensions of a class of FIFs are derived.

TL;DR: The main contribution of this paper is the development of a novel approach, based on the theory of Reproducing Kernel Hilbert Spaces, for the problem of noise removal in the spatial domain, which has the advantage that it is able to remove any kind of additive noise from any digital image, in contrast to the most commonly used denoising techniques, which are noise dependent.