From conventional wisdom and empirical studies of annotated data, it has been shown that visual statistics such as object frequencies and segment sizes follow power law distributi...
Alex Shyr, Trevor Darrell, Michael Jordan, Raquel ...
For many machine learning solutions to complex applications, there are significant performance advantages to decomposing the overall task into several simpler sequential stages, c...
Abstract Supervised classification is one of the tasks most frequently carried out by socalled Intelligent Systems. Thus, a large number of techniques have been developed based on ...
Sotiris B. Kotsiantis, Ioannis D. Zaharakis, Panay...
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
We propose a new semi-supervised model selection method that is derived by applying the structural risk minimization principle to a recent semi-supervised generalization error bou...