Most state-of-the-art approaches to action recognition rely on global representations either by concatenating local information in a long descriptor vector or by computing a single...
A combination of several classifiers using global features for the content description of medical images is proposed. Beside well known texture histogram features, downscaled repr...
The traditional SPM approach based on bag-of-features (BoF) must use nonlinear classifiers to achieve good image classification performance. This paper presents a simple but effec...
In situ staining of a target mRNA at several time points during the development of a D. melanogaster embryo gives one a detailed spatio-temporal view of the expression pattern of ...
Logical entity recognition in heterogeneous collections of document page images remains a challenging problem since the performance of traditional supervised methods degrade drama...