CONTINUOUS LEARNING OF SIMPLE VISUAL CONCEPTS USING INCREMENTAL KERNEL DENSITY ESTIMATION

Danijel Skočaj, Matej Kristan, Aleš Leonardis

2008

Abstract

In this paper we propose a method for continuous learning of simple visual concepts. The method continuously associates words describing observed scenes with automatically extracted visual features. Since in our setting every sample is labelled with multiple concept labels, and there are no negative examples, reconstructive representations of the incoming data are used. The associated features are modelled with kernel density probability distribution estimates, which are built incrementally. The proposed approach is applied to the learning of object properties and spatial relations.

References

  1. Fidler, S., Skoc?aj, D., Leonardis, A., Combining reconstructive and discriminative subspace methods for robust classification and regression by subsampling. IEEE Transactions on Pattern Analysis and Machine Intelligence 28 (2006) 337-350
  2. Harnad, S., The symbol grounding problem. Physica D: Nonlinear Phenomena 42 (1990) 335-346
  3. Ardizzone, E., Chella, A., Frixione, M., Gaglio, S., Integrating subsymbolic and symbolic processing in artificial vision. Journal of Intelligent Systems 1(4) (1992) 273-308
  4. Roy, D.K., Pentland, A.P., Learning words from sights and sounds: a computational model. Cognitive Science 26 (2002) 113-146
  5. Roy, D.K., Learning visually-grounded words and syntax for a scene description task. Computer Speech and Language 16(3) (2002) 353-385
  6. Vogt, P., The physical symbol grounding problem. Cognitive Systems Research 3 (2002) 429-457
  7. Kirstein, S., Wersing, H., Körner, E., Rapid online learning of objects in a biologically motivated recognition architecture. In: 27th DAGM. (2005) 301-308
  8. Steels, L., Kaplan, F., AIBO's first words. the social learning of language and meaning. Evolution of Communication 4 (2001) 3-32
  9. Arsenio, A., Developmental learning on a humanoid robot. In: IEEE International Joint Conference On Neural Networks. (2004) 3167-3172
  10. Wand, M.P., Jones, M.C., Kernel Smoothing. Chapman & Hall/CRC (1995)
  11. Elgammal, A., Duraiswami, R., Harwood, D., Davis, L., Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. In: Proceedings of the IEEE. (2002) 1151- 1163
  12. Han, B., Comaniciu, D., Davis, L., Sequential density approximation through mode propagation: Applications to background modeling. In: Asian Conf. Computer Vision. (2004)
  13. Arandjelovic, O., Cipolla, R., Incremental learning of temporally-coherent gaussian mixture models. In: British Machine Vision Conference. (2005) 759-768
  14. Song, M., Wang, H., Highly efficient incremental estimation of gaussian mixture models for online data stream clustering. In: SPIE: Intelligent Computing: Theory and Applications. (2005) 174-183
  15. Szewczyk, W.F., Time-evolving adaptive mixtures. Technical report, National Security Agency (2005)
  16. Julier, S., Uhlmann, J., A general method for approximating nonlinear transformations of probability distributions. Technical report, Department of Engineering Science, University of Oxford (1996)
  17. Leonardis, A., Bischof, H., An efficient MDL-based construction of RBF networks. Neural Networks 11(1998) 963 - 973
  18. Jones, M.C., Marron, J.S., Sheather, S.J., A brief survey of bandwidth selection for density estimation. J. Amer. Stat. Assoc. 91 (1996) 401-407
Download


Paper Citation


in Harvard Style

Skočaj D., Kristan M. and Leonardis A. (2008). CONTINUOUS LEARNING OF SIMPLE VISUAL CONCEPTS USING INCREMENTAL KERNEL DENSITY ESTIMATION . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: OPRMLT, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 598-604. DOI: 10.5220/0001090405980604


in Bibtex Style

@conference{oprmlt08,
author={Danijel Skočaj and Matej Kristan and Aleš Leonardis},
title={CONTINUOUS LEARNING OF SIMPLE VISUAL CONCEPTS USING INCREMENTAL KERNEL DENSITY ESTIMATION},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: OPRMLT, (VISIGRAPP 2008)},
year={2008},
pages={598-604},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001090405980604},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: OPRMLT, (VISIGRAPP 2008)
TI - CONTINUOUS LEARNING OF SIMPLE VISUAL CONCEPTS USING INCREMENTAL KERNEL DENSITY ESTIMATION
SN - 978-989-8111-21-0
AU - Skočaj D.
AU - Kristan M.
AU - Leonardis A.
PY - 2008
SP - 598
EP - 604
DO - 10.5220/0001090405980604