%0 Conference Proceedings
%T Classifying Objects at Different Sizes with Multi-Scale Stacked Sequential Learning
%A Eloi Puertas
%A Sergio Escalera
%A Oriol Pujol
%E R. Alquezar, A. Moreno
%B 13th International Conference of the Catalan Association for Artificial Intelligence
%D 2010
%V 220
%@ 978-1-60750-642-3
%F Eloi Puertas2010
%O HUPBA;MILAB
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=1448), last updated on Thu, 18 Jan 2018 11:59:31 +0100
%X Sequential learning is that discipline of machine learning that deals with dependent data. In this paper, we use the Multi-scale Stacked Sequential Learning approach (MSSL) to solve the task of pixel-wise classification based on contextual information. The main contribution of this work is a shifting technique applied during the testing phase that makes possible, thanks to template images, to classify objects at different sizes. The results show that the proposed method robustly classifies such objects capturing their spatial relationships.
%P 193–200