There are several pieces of information that can be utilized in order to improve the efficiency of similarity searches on high-dimensional data. The most commonly used information...
We present an automated Image Annotation system called I-Tag which uses both visual and textual information of the images and recommends relevant tags for them. The automatic gene...
In this paper we propose and evaluate an algorithm that learns a similarity measure for comparing never seen objects. The measure is learned from pairs of training images labeled ...
Motion estimation represents the most computationally intensive task for all efficient motion compensated compression standards. This fact, despite the several eflorts aiming at r...
The rapid development of web image search engines has enabled users to search hundred million of images available on the Web. However, due to the unsatisfactory performance of cur...