Advertisement

Modeling Action Verb Semantics Using Motion Tracking

  • Timo Honkela
  • Klaus Förger
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8131)

Abstract

In this article, we consider how semantics of action verbs can be grounded on motion tracking data. We present the basic principles and requirements for grounding of verbs through case studies related to human movement. The data includes high-dimensional movement patterns and linguistic expressions that people have used to name these movements. We discuss open issues and possibilities related to symbol grounding. As a conclusion, we find the grounding to be useful when reasoning about the meaning of words and relationships between them within one language and potentially also between languages.

Keywords

Motion Tracking Action Verb Neural Information Processing System Absolute Velocity Symbol Grounding 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hörmann, H.: Meaning and Context. Plenum Press, New York (1986)CrossRefGoogle Scholar
  2. 2.
    Choi, S., Bowerman, M.: Learning to express motion events in English and Korean: The influence of language-specific lexicalization patterns. Cognition 41(1), 83–121 (1991)CrossRefGoogle Scholar
  3. 3.
    Harnad, S.: The symbol grounding problem. Physica D 42, 335–346 (1990)CrossRefGoogle Scholar
  4. 4.
    Pavlović, V., Rehg, J., MacCormick, J.: Learning switching linear models of human motion. In: Advances in Neural Information Processing Systems 13, pp. 981–987 (2001)Google Scholar
  5. 5.
    Taylor, G.W., Hinton, G.E., Roweis, S.: Modeling human motion using binary latent variables. In: Advances in Neural Information Processing Systems 19, pp. 1345–1352 (2007)Google Scholar
  6. 6.
    Davis, J., Gao, H.: Gender recognition from walking movements using adaptive three-mode PCA. In: Computer Vision and Pattern Recognition Workshop (2004)Google Scholar
  7. 7.
    Roy, D.: Grounding words in perception and action: computational insights. Trends in Cognitive Sciences 9(8), 389–396 (2005)CrossRefGoogle Scholar
  8. 8.
    Williams, M.A., McCarthy, J., Gärdenfors, P., Stanton, C., Karol, A.: A grounding framework. Autonomous Agents and Multi-Agent Systems 19(3), 272–296 (2009)CrossRefGoogle Scholar
  9. 9.
    Lakoff, G., Johnson, M.: Philosophy in the Flesh - The Embodied Mind and its Challenge to Western Thought. John Wiley, New York (1999)Google Scholar
  10. 10.
    Glenberg, A.M., Robertson, D.A.: Symbol grounding and meaning: A comparison of high-dimensional and embodied theories of meaning. Journal of Memory and Language 43(3), 379–401 (2000)CrossRefGoogle Scholar
  11. 11.
    Sun, R.: Symbol grounding: a new look at an old idea. Philosophical Psychology 13(2), 149–172 (2000)CrossRefGoogle Scholar
  12. 12.
    Vogt, P.: The physical symbol grounding problem. Cognitive Systems Research 3(3), 429–457 (2002)CrossRefGoogle Scholar
  13. 13.
    Gärdenfors, P., Warglien, M.: Using conceptual spaces to model actions and events. Journal of Semantics 29(4), 487–519 (2012)CrossRefGoogle Scholar
  14. 14.
    Bailey, D.: When Push Comes to Shove: A Computational Model of the Role of Motor Control in the Acquisition of Action Verbs. PhD thesis, UC Berkeley (1997)Google Scholar
  15. 15.
    Honkela, T.: Philosophical aspects of neural, probabilistic and fuzzy modeling of language use and translation. In: Proceedings of IJCNN 2007, pp. 2881–2886 (2007)Google Scholar
  16. 16.
    Li, W.: Zipf’s law everywhere. Glottometrics 5, 14–21 (2002)MATHGoogle Scholar
  17. 17.
    Shoemake, K.: Animating rotation with quaternion curves. SIGGRAPH Computer Graphics 19(3), 245–254 (1985)CrossRefGoogle Scholar
  18. 18.
    Kohonen, T.: Self-Organizing Maps. Springer (2001)Google Scholar
  19. 19.
    Ji, R., Yao, H., Liu, W., Sun, X., Tian, Q.: Task-dependent visual-codebook compression. IEEE Transactions on Image Processing 21(4), 2282–2293 (2012)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Honkela, T., Raitio, J., Nieminen, I., Lagus, K., Honkela, N., Pantzar, M.: Using GICA method to quantify epistemological subjectivity. In: Proc. of IJCNN 2012, pp. 2875–2883 (2012)Google Scholar
  21. 21.
    Sjöberg, M., Viitaniemi, V., Laaksonen, J., Honkela, T.: Analysis of semantic information available in an image collection augmented with auxiliary data. In: Proc. of AIAI 2006, Artificial Intelligence Applications and Innovations, pp. 600–608. Springer (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Timo Honkela
    • 1
  • Klaus Förger
    • 2
  1. 1.Department of Information and Computer ScienceAalto University School of ScienceAaltoFinland
  2. 2.Department of Media TechnologyAalto University School of ScienceAaltoFinland

Personalised recommendations