English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Learning the Influence of Spatio-Temporal Variations in Local Image Structure on Visual Saliency

Kienzle, W., Wichmann, F., Schölkopf, B., & Franz, M. (2007). Learning the Influence of Spatio-Temporal Variations in Local Image Structure on Visual Saliency. Poster presented at 10th Tübinger Wahrnehmungskonferenz (TWK 2007), Tübingen, Germany.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-CCE9-A Version Permalink: http://hdl.handle.net/21.11116/0000-0003-FF5D-7
Genre: Poster

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Kienzle, W1, 2, Author              
Wichmann, FA1, 2, Author              
Schölkopf, B1, 2, Author              
Franz, MO1, 2, Author              
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Computational models for bottom-up visual attention traditionally consist of a bank of Gabor-like or Difference-of-Gaussians filters and a nonlinear combination scheme which combines the filter responses into a real-valued saliency measure [1]. Recently it was shown that a standard machine learning algorithm can be used to derive a saliency model from human eye movement data with a very small number of additional assumptions. The learned model is much simpler than previous models, but nevertheless has state-of-the-art prediction performance [2]. A central result from this study is that DoG-like center-surround filters emerge as the unique solution to optimizing the predictivity of the model. Here we extend the learning method to the temporal domain. While the previous model [2] predicts visual saliency based on local pixel intensities in a static image, our model also takes into account temporal intensity variations. We find that the learned model responds strongly to temporal intensity changes ocurring 200-250ms before a saccade is initiated. This delay coincides with the typical saccadic latencies, indicating that the learning algorithm has extracted a meaningful statistic from the training data. In addition, we show that the model correctly predicts a significant proportion of human eye movements on previously unseen test data.

Details

show
hide
Language(s):
 Dates: 2007-07
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Degree: -

Event

show
hide
Title: 10th Tübinger Wahrnehmungskonferenz (TWK 2007)
Place of Event: Tübingen, Germany
Start-/End Date: 2007-07-27 - 2007-07-29

Legal Case

show

Project information

show

Source 1

show
hide
Title: 10th Tübinger Perception Conference: TWK 2007
Source Genre: Proceedings
 Creator(s):
Bülthoff, HH1, Editor            
Chatziastros, A1, Editor            
Mallot, HA, Editor            
Ulrich, R, Editor
Affiliations:
1 Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797            
Publ. Info: Kirchentellinsfurt, Germany : Knirsch
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 63 Identifier: ISBN: 3-927091-77-4