State-of-the-art object retrieval systems are mostly based on the bag-of-visual-words representation which encodes local appearance information of an image in a feature vector. A ...
Today's Content-Based Image Retrieval (CBIR) techniques are based on the "k-nearest neighbors" (kNN) model. They retrieve images from a single neighborhood using lo...
Multiple Instance Learning (MIL) is a special kind of supervised learning problem that has been studied actively in recent years. We propose an approach based on One-Class Support ...
This paper presents a method for classifying the direction of movement and for segmenting objects simultaneously using features of space-time patches. Our approach uses vector quan...
We describe a compressed multiresolution representation for supporting interactive rendering of very large planar and spherical terrain surfaces. The technique, called Compressed ...
Enrico Gobbetti, Fabio Marton, Paolo Cignoni, Marc...