Learning Features of Intermediate Complexity for the Recognition of Biological Motion

  • Rodrigo Sigala
  • Thomas Serre
  • Tomaso Poggio
  • Martin Giese
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3696)


Humans can recognize biological motion from strongly impoverished stimuli, like point-light displays. Although the neural mechanism underlying this robust perceptual process have not yet been clarified, one possible explanation is that the visual system extracts specific motion features that are suitable for the robust recognition of both normal and degraded stimuli. We present a neural model for biological motion recognition that learns robust mid-level motion features in an unsupervised way using a neurally plausible memory-trace learning rule. Optimal mid-level features were learnt from image motion sequences containing a walker with, or without background motion clutter. After learning of the motion features, the detection performance of the model substantially increases, in particular in presence of clutter. The learned mid-level motion features are characterized by horizontal opponent motion, where this feature type arises more frequently for the training stimuli without motion clutter. The learned features are consistent with recent psychophysical data that indicates that opponent motion might be critical for the detection of point light walkers.


Motion Feature Intermediate Complexity Biological Motion Point Light Walker Opponent Motion 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Born, R.T.: Center-surround interactions in the middle temporal visual area of the owl monkey. J. Neurophysiol. 84, 2658–2669 (2000)Google Scholar
  2. 2.
    Casile, A., Giese, M.: Critical features for the recognition of biological motion. Journal of Vision 5, 348–360 (2005)CrossRefGoogle Scholar
  3. 3.
    Földiak, P.: Learning invariance from transformation sequences. Neural Computation 3, 194–200 (1991)CrossRefGoogle Scholar
  4. 4.
    Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36, 193–202 (1980)zbMATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Giese, M.A., Poggio, T.: Neural mechanisms for the recognition of biological movements and action. Nature Reviews Neuroscience 4, 179–192 (2003)CrossRefGoogle Scholar
  6. 6.
    Johansson, G.: Visual perception of biological motion and a model for its analysis. Perc. Psychophys. 14, 201–211 (1973)CrossRefGoogle Scholar
  7. 7.
    Mather, G., Radford, K., West, S.: Low-level visual processing of biological motion. Proc. R. Soc. Lon. B 249(1325), 149–155 (1992)CrossRefGoogle Scholar
  8. 8.
    Riesenhuber, M., Poggio, T.: Hierarchical models for object recognition in cortex. Nat. Neuroscience 2, 1019–1025 (1999)CrossRefGoogle Scholar
  9. 9.
    Serre, T., Poggio, T.: Learning a vocabulary of shape-components in visual cortex (2005) (In Prep.)Google Scholar
  10. 10.
    Sigala, R.: A Neural Mechanism to Learn Features of Intermediate Complexity in the Form and Motion Visual Pathway of Cortex. Thesis MSc. in Neural and Behavioural Sciences, MPI International Research School, Tuebingen, Germany (2005)Google Scholar
  11. 11.
    Song, Y., Goncalves, L., Perona, P.: Unsupervised Learning of Human Motion Models. In: Advances in Neural Information Processing Systems 14, Vancouver, Cannada (2001)Google Scholar
  12. 12.
    Tanaka, K., Fukuda, Y., Saito, H.: Analysis of motion of the visual field by direction, expansion/contraction, and rotation cells clustered in the dorsal part of the medial superior temporal area of the macaque monkey. J. Neurophysiol. 62, 626–641 (1989)Google Scholar
  13. 13.
    Vapnik, V.: Statistical Learning Theory. John Wiley and Sons, New York (1998)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Rodrigo Sigala
    • 1
    • 2
  • Thomas Serre
    • 2
  • Tomaso Poggio
    • 2
  • Martin Giese
    • 1
  1. 1.Laboratory for Action Representation and Learning (ARL), Dept. of Cognitive NeurologyUniversity Clinic TübingenTübingenGermany
  2. 2.McGovern Institute for Brain Research, Brain and Cognitive Sciences, MassachusettsInstitute of TechnologyCambridgeUSA

Personalised recommendations