In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
We develop an automatic system to analyze subtle changes in upper face expressions based on both permanent facial features (brows, eyes, mouth)andtransient facial features (deepen...
In this paper, an original motion-based shape error concealment technique, especially useful for object-based video applications in error-prone environments such as mobile network...
In recent years, research about distributing databases over networks has become increasingly important. Here we concentrate on the issues of interoperability of heterogeneous DBMS...
Stefan Grufman, Fredrik Samson, Suzanne M. Embury,...
Complete and accurate video tracking is very difficult to achieve in practice due to long occlusions, traffic clutter, shadows and appearance changes. In this paper, we study the ...
Anthony Hoogs, Gianfranco Doretto, John Schmiedere...