We cope with the metadata recognition in layoutoriented documents. We address the problem as a classification task and propose a method for automatic extraction of relevant featu...
Digital visual libraries have currently available huge amounts of content in unstructured, nonindexed form. Since these collections keep growing fast, retrieving specific images i...
In this letter, a novel modular neural network (MNN) classifier, which partitions a K-class problem into many much easier two-class problems in sub-subspaces, was proposed to per...
In this paper, we propose a new method to extract moving objects from a video stream without any motion estimation. The objective is to obtain a method robust to noise, large motio...
Loic Biancardini, Eva Dokladalova, Serge Beucher, ...
We introduce the first visual dataset of fast foods with a total of 4,545 still images, 606 stereo pairs, 303 3600 videos for structure from motion, and 27 privacy-preserving vide...