Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  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

Externe Referenzen

einblenden:
ausblenden:
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Kienzle, W1, 2, Autor           
Wichmann, FA1, 2, Autor           
Schölkopf, B1, 2, Autor           
Franz, MO1, 2, Autor           
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              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: 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

einblenden:
ausblenden:
Sprache(n):
 Datum: 2007-07
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: URI: http://www.twk.tuebingen.mpg.de/twk07/abstract.php?_load_id=kienzle01
BibTex Citekey: 4854
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 10th Tübinger Wahrnehmungskonferenz (TWK 2007)
Veranstaltungsort: Tübingen, Germany
Start-/Enddatum: 2007-07-27 - 2007-07-29

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: 10th Tübinger Perception Conference: TWK 2007
Genre der Quelle: Konferenzband
 Urheber:
Bülthoff, HH1, Herausgeber           
Chatziastros, A1, Herausgeber           
Mallot, HA, Herausgeber           
Ulrich, R, Herausgeber
Affiliations:
1 Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797            
Ort, Verlag, Ausgabe: Kirchentellinsfurt, Germany : Knirsch
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 63 Identifikator: ISBN: 3-927091-77-4