Hierarchical Selectivity for Object-Based Visual Attention

  • Yaoru Sun
  • Robert Fisher
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2525)


This paper presents a novel “hierarchical selectivity” mechanism for object-based visual attention. This mechanism integrates visual salience from bottom-up groupings and the top-down attentional setting. Under its guidance, covert visual attention can shift not only from one grouping to another but also from a grouping to its sub-groupings at a single resolution or multiple varying resolutions. Both object-based and space-based selection is integrated to give a visual attention mechanism that has multiple and hierarchical selectivity.


Visual Attention Visual Salience Outdoor Scene Goto Step Current Resolution 
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.
    S. Baluja, and D. Pomerleau, “Dynamic relevance: Vision-based focus of attention using artificial neural networks,” Artificial Intelligence, 97, pp. 381–395, 1997.CrossRefzbMATHGoogle Scholar
  2. 2.
    M. Behrmann, R. S. Zemel, and M. C. Mozer, “Occlusion, symmetry, and objectbased attention: reply to Saiki (2000),” Journal of Experimental Psychology: Human Perception and Performance, 26(4), pp. 1497–1505, 2000.CrossRefGoogle Scholar
  3. 3.
    C. Koch and S. Ullman, “Shifts in selective visual attention: towards the underlying neural circuity,” Human Neurobiology, 4:481–484, 1985.Google Scholar
  4. 4.
    R. Desimone, and J. Duncan, “Neural mechanisms of selective visual attention,” Ann. Rev. Neurosci., 18, pp. 193–222, 1995.CrossRefGoogle Scholar
  5. 5.
    R. Desimone, “Visual attention mediated by biased competition in extrastriate visual cortex,” Phil. Trans. R. Soc. Lond. B, 353, pp. 1245–1255, 1998.CrossRefGoogle Scholar
  6. 6.
    J. Duncan, “Converging levels of analysis in the cognitive neuroscience of visual attention,” Phil. Trans. R. Soc. Lond. B., 353, pp. 1307–1317, 1998.CrossRefGoogle Scholar
  7. 7.
    H. Greenspan, S. Belongie, R. Goodman, P. Persona, S. Rakshit, and C. H. Anderson, “Overcomplete steerable pyramid filters and rotation invariance,” In proc. IEEE Computer Vision and Pattern Recognition, pp. 222–228, Seattle, Washington, 1994.Google Scholar
  8. 8.
    L. Itti, C. Koch, and E. Niebur, “A model of saliency-based visual attention for rapid scene analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(11), pp. 1254–1259, 1998.CrossRefGoogle Scholar
  9. 9.
    L. Itti and C. Koch, “Salience-Based serach mechanism for overt and covert shifts of visual attention,” 40(10–12):1489–1506, 2000.Google Scholar
  10. 10.
    S. Kastner and L. G. Ungerleider, “Mechanisms of visual attention in the human cortex,” Annu. Rev. Neurosci., 23:315–341, 2002.Google Scholar
  11. 11.
    S. E. Palmer, Vision Science-Photons to Phenomenology, Cambridge, MA: MIT Press, 1999.Google Scholar
  12. 12.
    B. J. Scholl, “Objects and attention: the state of the art,” Cognition, 80, pp. 1–46, 2001.CrossRefGoogle Scholar
  13. 13.
    J. K. Tsotsos, et al. “Modelling visual attention via selective tuning,” Artificial Intelligence, 78, pp. 507–545, 1995.MathSciNetCrossRefGoogle Scholar
  14. 14.
    Yaoru Sun and Robert Fisher, “Object-based visual attention for computer vision,” submitted to Artificial Intelligence.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Yaoru Sun
    • 1
  • Robert Fisher
    • 1
  1. 1.Division of InformaticsUniversity of EdinburghEdinburghUK

Personalised recommendations