In this paper we propose a novel method for learning a Mahalanobis distance measure to be used in the KNN classification algorithm. The algorithm directly maximizes a stochastic v...
Jacob Goldberger, Sam T. Roweis, Geoffrey E. Hinto...
Experience in preparing Web content for people with visual disabilities shows that automatic testing of accessibility is clearly insufficient to meet real-world demands, and that ...
Today, it is possible to acquire volume representations of the vessel structures in the brain. The selfadjusting probe, a new tool introduced in a previous paper, enables semi-aut...
This paper describes a new method for creating visually realistic moving facial image sequences that retain an actor's personality (individuality, expression and characterist...
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...