Agradecimentos: We would like thank Nguyen Vu Hoàng for the discussion on the description of spatial relationships. We also would like to thank Fapesp (Grant nos. 2009/10554-8, 2009/05951-8, and 2012/16172-2), CNPq (Grant nos. 484254/2012-0 and 306580/2012-8), Capes, Samsung, and Microsoft Research for infrastructure and financial support Ver menos

Abstract: We present word spatial arrangement (WSA), an approach to represent the spatial arrangement of visual words under the bag-of-visual-words model. It lies in a simple idea which encodes the relative position of visual words by splitting the image space into quadrants using each detected point as origin. WSA generates compact feature vectors and is flexible for being used for image retrieval and classification, for working with hard or soft assignment, requiring no pre/post processing for spatial verification. Experiments in the retrieval scenario show the superiority of WSA in relation to Spatial Pyramids. Experiments in the classification scenario show a reasonable compromise between those methods, with Spatial Pyramids generating larger feature vectors, while WSA provides adequate performance with much more compact features. As WSA encodes only the spatial information of visual words and not their frequency of occurrence, the results indicate the importance of such information for visual categorization Ver menos