Learning object categories from small samples is a challenging problem, where machine learning tools can in general provide very few guarantees. Exploiting prior knowledge may be ...
Tatiana Tommasi, Francesco Orabona, Barbara Caputo
This paper reports the work on a novel wavelet-based multi-scale filtering application used to generate very smooth subset of profiles known as Class-A curves. The multi-scale rep...
- We report classification experiments using the pilot Infant COPE database of neonatal facial expressions. Two sets of DCT coeffiecents were used to train a neural network simulta...
Structured peer-to-peer systems rely on replication as a basic means to provide fault-tolerance in presence of high churn. Most select replicas using either multiple hash functions...
This paper presents the result of an adaptive region growing segmentation technique for color document images using an irregular pyramid structure. The emphasis is in the segmentat...