A System for Continuous Learning of Visual Concepts

Authors

  • Danijel Skocaj
  • Gregor Berginc
  • Barry Ridge
  • Ales Stimec
  • Matjaz Jogan
  • Ondrej Vanek
  • Ales Leonardis
  • Manuela Hutter
  • Nick Hawes

DOI:

https://doi.org/10.2390/biecoll-icvs2007-113

Keywords:

symbol grounding, associations, cross-modal learning, continuous learning, cognitive vision system, DDC: 004 (Data processing, computer science, computer systems)

Abstract

We present an artificial cognitive system for learning visual concepts. It comprises of vision, communication and manipulation subsystems, which provide visual input, enable verbal and non-verbal communication with a tutor and allow interaction with a given scene. The main goal is to learn associations between automatically extracted visual features and words that describe the scene in an open-ended, continuous manner. In particular, we address the problem of cross-modal learning of visual properties and spatial relations. We introduce and analyse several learning modes requiring different levels of tutor supervision.

Downloads

Published

2007-12-31

Issue

Section

The 5th International Conference on Computer Vision Systems