Learning to Attend — From Bottom-Up to Top-Down

  • Hector Jasso
  • Jochen Triesch
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4840)


The control of overt visual attention relies on an interplay of bottom-up and top-down mechanisms. Purely bottom-up models may provide a reasonable account of the looking behaviors of young infants, but they cannot accurately account for attention orienting of adults in many natural behaviors. But how do humans learn to incorporate top-down mechanisms into their control of attention? The phenomenon of gaze following, i.e. the ability to infer where someone else is looking and to orient to the same location, offers an interesting window into this question. We review findings on the emergence of gaze following in human infants and present a computational model of the underlying learning processes. The model exhibits a gradual incorporation of top-down cues in the infant’s attention control. It explains this process in terms of generic reinforcement learning mechanisms. We conclude that reinforcement learning may be a major driving force behind the incorporation of top-down cues into the control of visual attention.


Visual Search Visual Attention Reinforcement Learning Joint Attention Mirror Neuron 
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.
    Itti, L., Koch, C.: A saliency-based search mechanism for overt and covert shift of visual attention. Vision Research 40, 1489–1506 (2000)CrossRefGoogle Scholar
  2. 2.
    Yarbus, A.L.: Eye movements during perception of complex objects. In: Riggs, L.A. (ed.) Eye Movements and Vision, Ch. VII, pp. 171–196. Plenum Press, New York (1967)CrossRefGoogle Scholar
  3. 3.
    Land, M.F., Mennie, N., Rusted, J.: The roles of vision and eye movements in the control of activities of daily living. Perception 28, 1311–1328 (1999)CrossRefGoogle Scholar
  4. 4.
    Land, M.F., Hayhoe, M.M.: In what ways do eye movements contribute to everyday activities? Vision Research 41, 3559–3565 (2001)CrossRefGoogle Scholar
  5. 5.
    Hayhoe, M., Land, M., Shrivastava, A.: Coordination of eye and hand movements in a normal environment. Invest. Ophthalmol & Vis. Sci. 40, S380 (1999)Google Scholar
  6. 6.
    Wolfe, J.M.: Visual search. In: Pashler, H. (ed.) Attention, University College London Press, London, UK (1998)Google Scholar
  7. 7.
    Haith, M.M., Hazan, C., Goodman, G.S.: Expectation and anticipation of dynamic visual events by 3.5-month-old babies. Child Development 59, 467–479 (1988)CrossRefGoogle Scholar
  8. 8.
    Dayan, P., Abbott, L.F.: Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems. MIT Press, Cambridge, MA, USA (2001)zbMATHGoogle Scholar
  9. 9.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning. MIT Press, Cambridge, MA (1998)Google Scholar
  10. 10.
    Scaife, M., Bruner, J.: The capacity for joint visual attention in the infant. Nature 253, 265–266 (1975)CrossRefGoogle Scholar
  11. 11.
    Butterworth, G.E., Cochran, E.: Towards a mechanism of joint visual attention in human infancy. International Journal of Behavioral Development 3, 253–272 (1980)CrossRefGoogle Scholar
  12. 12.
    Butterworth, G.E., Jarrett, N.: What minds have in common is space: Spatial mechanisms serving joint visual attention in infancy. British Journal of Developmental Psychology 9, 55–72 (1991)CrossRefGoogle Scholar
  13. 13.
    Deák, G., Flom, R.A., Pick, A.D.: Effects of Gesture and Target on 12- and 18-Month-Olds’ Joint Visual Attention to Objects in Front of or Behind Them. Developmental Psychology 36, 511–523 (2000)CrossRefGoogle Scholar
  14. 14.
    Brooks, R., Meltzoff, A.N.: The importance of eyes: How infants interpret adult looking behavior. Developmental Psychology 38, 958–966 (2002)CrossRefGoogle Scholar
  15. 15.
    Brooks, R., Meltzoff, A.N.: The development of gaze following and its relation to language. Developmental Science 8, 535–543 (2005)CrossRefGoogle Scholar
  16. 16.
    Meltzoff, A.N., Brooks, R.: Eyes wide shut: The importance of eyes in infant gaze following and understanding of other minds. In: Flom, R., Lee, K., Muir, D. (eds.) Gaze following: Its development and significance, pp. 217–241. Lawrence Erlbaum, Mahwah, NJ (2007)Google Scholar
  17. 17.
    Mundy, P., Sigman, M., Kasari, C.: A longitudinal study of joint attention and language development in autistic children. Journal of Autism and Developmental Disorders 20, 115–128 (1990)CrossRefGoogle Scholar
  18. 18.
    Treisman, A., Gelade, G.: A feature integration theory of attention. Cognitive Psychology 12, 97–136 (1980)CrossRefGoogle Scholar
  19. 19.
    Brooks, R., Breazeal, C., Marjanovic, M., Scassellati, B., Williamson, M.: The Cog Project: Building a Humanoid Robot. In: Nehaniv, C.L. (ed.) Computation for Metaphors, Analogy, and Agents. LNCS (LNAI), vol. 1562, Springer, Heidelberg (1999)Google Scholar
  20. 20.
    Kozima, H., Yano, H.: A robot that learns to communicate with human caregivers. In: First International Workshop on Epigenetic Robotics, Lund, Sweden (2001)Google Scholar
  21. 21.
    Kozima, H.: Infanoid: A babybot that explores the social environment. In: Dautenhahn, K., Bond, A.H., Canamero, L., Edmonds, B. (eds.) Socially Intelligent Agents: Creating Relationships with Computers and Robots, pp. 157–164. Kluwer Academic Publishers, Amsterdam (2002)CrossRefGoogle Scholar
  22. 22.
    Nagai, Y., Hosoda, K., Morita, A., Asada, M.: A constructive model for the development of joint attention. Connection Science 15, 211–229 (2003)CrossRefGoogle Scholar
  23. 23.
    Nagai, Y., Asada, M., Hosoda, K.: Learning for joint attention helped by functional development. Advanced Robotics 20(10), 1165–1181 (2006)CrossRefGoogle Scholar
  24. 24.
    Hoffman, M.W., Grimes, D.B., Shon, A.P., Rao., R.P.N.: A probabilistic model of gaze imitation and shared attention. Neural Networks 19, 299–310 (2006)CrossRefzbMATHGoogle Scholar
  25. 25.
    Matsuda, G., Omori, T.: Learning of Joint Visual Attention by Reinforcement Learning. In: Altmann, E.M., Cleeremans, A. (eds.) Proceedings of the fourth international conference on cognitive modeling, pp. 157–162. Lawrence Erlbaum Associates, Mahwah, NL (2001)Google Scholar
  26. 26.
    Triesch, J., Teuscher, C., Deák, G.O., Carlson, E.: Gaze following: why (not) learn it? Developmental Science 9, 125–157 (2006)CrossRefGoogle Scholar
  27. 27.
    Lau, B., Triesch, J.: Learning gaze following in space: a computational model. In: ICDL 2004. 3rd International Conference for Development and Learning, La Jolla, California, USA, pp. 20–22 (October 2004)Google Scholar
  28. 28.
    Daly, S., Matthews, K., Ribas-Corbera, J.: Visual eccentricity models in face-based video compression. In: IS&SPIE Conference on Human Vision and Electronic Imaging IV, San Jose, California, USA (January 1999)Google Scholar
  29. 29.
    Stanley, J.C.: Computer simulation of a model of habituation. Nature 261, 146–148 (1976)CrossRefGoogle Scholar
  30. 30.
    Farroni, T., Csibra, G., Simion, F., Johnson, M.H.: Eye contact detection in humans from birth. Proc. Natl. Acad. Sci. USA 99, 9602–9605 (2002)CrossRefGoogle Scholar
  31. 31.
    Li, Z.: Contextual influences in V1 as a basis for pop out and asymmetry in visual search. Proceedings of the National Academy of Sciences 96, 10530–10535 (1999)CrossRefGoogle Scholar
  32. 32.
    Li, Z.: A saliency map in primary visual cortex. Trends in Cognitive Science 6, 9–16 (2002)CrossRefGoogle Scholar
  33. 33.
    von Hofsten, C., Dahlström, E., Fredriksson, Y.: 12-month-old infants’ perception of attention direction in static video images. Infancy 8, 217–231 (2005)CrossRefGoogle Scholar
  34. 34.
    Anstis, S.M., Mayhew, J.W., Morley, T.: The perception of where a face or television ‘portrait’ is looking. American Journal of Psychology 82, 474–489 (1969)CrossRefGoogle Scholar
  35. 35.
    Cline, M.G.: The perception of where a person is looking. American Journal of Psychology 80, 41–50 (1967)CrossRefGoogle Scholar
  36. 36.
    Gibson, J.J., Pick, A.: Perception of another person’s looking behavior. American Journal of Psychology 76, 386–394 (1963)CrossRefGoogle Scholar
  37. 37.
    Jenkins, R., Beaver, J.D., Calder, A.J.: I thought you were looking at me! Direction-specific aftereffects in gaze perception. Psychological Science 17, 506–514 (2006)CrossRefGoogle Scholar
  38. 38.
    Schultz, W., Dayan, P., Montague, P.R.: A neural substrate of prediction and reward. Nature 275, 1593–1599 (1997)Google Scholar
  39. 39.
    Triesch, J., Jasso, H., Deák, G.O.: Emergency of Mirror Neurons in a Model of Gaze Following. Adaptive Behavior 15, 149–165 (2007)CrossRefGoogle Scholar
  40. 40.
    Fasel, I., Deák, G.O., Triesch, J., Movellan, J.: Combining Embodied Models and Empirical Research for Understanding the Development of Shared Attention. In: ICDL 2002. Proceedings of the International Conference on Development and Learning, Boston, MA, USA (2002)Google Scholar
  41. 41.
    Johnson, M.H., Dziurawiec, S., Ellis, H.D., Morton, J.: Newborns’ preferential tracking of face-like stimuli and its subsequent decline. Cognition 40, 1–19 (1991)CrossRefGoogle Scholar
  42. 42.
    Valenza, E., Simion, F., Cassia, V.M., Umiltá, C.: Face preference at birth. J. Exp. Psychol. Hum. Percept. Perform 22, 892–903 (1996)CrossRefGoogle Scholar
  43. 43.
    Murray, L., Trevarthen, C.: Emotion regulation of the interactions between two-month-olds and their mothers. In: Field, T., Fox, N. (eds.) Social perception in infants, pp. 89–111. Ablex, Norwood, NJ (1985)Google Scholar
  44. 44.
    Roberts, S., Pashler, H.: How persuasive is a good fit? A comment on theory testing. Psychological Review 107, 358–367 (2000)CrossRefGoogle Scholar
  45. 45.
    Jasso, H., Triesch, J., Deák, G.O.: A reinforcement learning model explains the development of gaze following. In: ICCM 2006. Proceedings of the 7th International Conference on Cognitive Modeling, Trieste, Italy (2006)Google Scholar
  46. 46.
    Jasso, H., Triesch, J.: Using eye direction cues for gaze following - a developmental model. In: ICDL 2006. Proceedings of the 5th International Conference on Development and Learning, Bloomington, IN, USA (2006)Google Scholar
  47. 47.
    Jasso, H.: A reinforcement learning model of gaze following. Unpublished Ph.D. dissertation. University of California, San Diego (2007)Google Scholar
  48. 48.
    Adrien, J.L., Lenoir, P., Martineau, J., Perrot, A., Hameury, L., Larmande, C., Sauvage, D.: Blind ratings of early symptoms of autism based upon family home movies. Journal of the American Academy of Child and Adolescent Psychiatry 32, 617–626 (1993)CrossRefGoogle Scholar
  49. 49.
    Hutt, C., Ounsted, C.: The biological significance of gaze aversion with particular reference to the syndrome of infantile autism. Behavioral Science 11(5), 346–356 (1966)CrossRefGoogle Scholar
  50. 50.
    Itti, L., Koch, C.: Computational modelling of visual attention. Nature Reviews Neuroscience 2, 194–203 (2001)CrossRefGoogle Scholar
  51. 51.
    Zhaoping, L.: A saliency map in primary visual cortex. Trends in Cognitive Sciences 6, 9–16 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Hector Jasso
    • 1
  • Jochen Triesch
    • 2
    • 3
  1. 1.Dept. of Computer Science and Engineering, University of California, San Diego, La Jolla, CA 92093USA
  2. 2.Frankfurt Institute for Advanced Studies, J.W. Goethe University, Frankfurt am MainGermany
  3. 3.Dept. of Cognitive Science, University of California, San Diego, La Jolla, CA 92093USA

Personalised recommendations