Visual Bootstrapping for Unsupervised Symbol Grounding

Abstract

Bibtex entry

@inproceedings{Kittler-ACIVS06,
        Abstract = { Most existing cognitive architectures integrate
                     computer vision and symbolic reasoning.  However,
                     there is still a gap between low-level scene
                     representations (signals) and abstract symbols.
                     Manually attaching, i.e. grounding, the symbols
                     on the physical context makes it impossible to
                     expand system capabilities by learning new
                     concepts.  This paper presents a visual
                     bootstrapping approach for the unsupervised
                     symbol grounding.  The method is based on a
                     recursive clustering of a perceptual category
                     domain controlled by goal acquisition from the
                     visual environment.  The novelty of the method
                     consists in division of goals into the classes of
                     parameter goal, invariant goal and context goal.
                     The proposed system exhibits incremental learning
                     in such a manner as to allow effective
                     transferable representation of high-level
                     concepts. },
        Author = {J Kittler and M Shevchenko and D Windridge},
        Booktitle = {Proceedings of 8th Advanced Concepts for Intelligent Vision 
                     Systems International Conference},
        Date-Added = {2007-08-09 14:12:12 +0200},
        Date-Modified = {2007-08-09 14:12:12 +0200},
        Editor = {J Blanc-Talon and W Philips and D Popescu and P Scheunders},
        Month = {September},
        Pages = {1037--1046},
        Publisher = {Springer},
        Title = {Visual Bootstrapping for Unsupervised Symbol Grounding},
        Year = {2006}}