The segmentation of pixels belonging to different moving elements within a cinematographic image sequence underpins a range of post-production special effects. In this work, the s...
We address the problem of classifying scenes from feature films into semantic categories and propose a robust framework for this problem. We propose that the Finite State Machines ...
Silhouettes contain rich information about the shape of objects that can be used for recognition and classification. We present a novel approach that allows us to reliably compute...
Lena Gorelick, Meirav Galun, Eitan Sharon, Ronen B...
In this work we compare the use of a Particle Swarm Optimization (PSO) and a Genetic Algorithm (GA) (both augmented with Support Vector Machines SVM) for the classification of high...
When the available information is imperfect, it is often desirable to represent it in the database, so that it can be used to answer queries of interest as much as possible. The da...