Similarity-based Acquisition of Spatial Categories

P. Papadopoulos

A very natural approach to categorization is similarity-based clustering. We propose a visual representation which can be used with such a mechanism for the acquisition of spatial relation categories. We also show how supervision can be helpful in cases where basic similarity is low by proposing a learning mechanism which operates both in the presence and in the absence of words.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.