We propose a fully automatic method for summarizing and indexing unstructured presentation videos based on text extracted from the projected slides. We use changes of text in the ...
Abstract. In this work, we propose a novel extension of pseudo 2D image warping (P2DW) which allows for joint alignment and recognition of non-rectified face images. P2DW allows f...
Leonid Pishchulin, Tobias Gass, Philippe Dreuw, He...
Human eyes are highly efficient devices for scanning through a large quantity of low-level visual sensory data and delivering selective information to one’s brain for high-level...
Today’s users want to access their data everywhere and any time – in various environments and occasions. The data itself can be very complex – the problem is then in providi...
Vladislav Nemec, Pavel Zikovsky, Pavel Slaví...
This paper presents the Visual Touchpad, a low-cost vision-based input device that allows for fluid two-handed interactions with desktop PCs, laptops, public kiosks, or large wall...