Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 20, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Methods for comparing scanpaths and saliency maps: strengths and weaknesses.

Olivier Le Meur1, Thierry Baccino

  • 1Université de Rennes 1. IRISA, Campus universitaire de Beaulieu, 35042, Rennes, France. olemeur@irisa.fr

Behavior Research Methods
|July 10, 2012
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Classifying musical reading expertise by eye-movement analysis using machine learning.

Frontiers in cognition·2026
Same author

Saccadic and visuo-motor flexibility towards local parafoveal complexity as a hallmark of expert knowledge-driven processing during sight-reading of music.

Quarterly journal of experimental psychology (2006)·2025
Same author

Markers of musical expertise in a sight-reading task: An eye-tracking study.

Journal of experimental psychology. Learning, memory, and cognition·2024
Same author

A narrative review of the interconnection between pilot acute stress, startle, and surprise effects in the aviation context: Contribution of physiological measurements.

Frontiers in neuroergonomics·2024
Same author

A Meta-analysis on the Effect of Expertise on Eye Movements during Music Reading.

Journal of eye movement research·2023
Same author

Fluctuation in cognitive engagement during listening and reading of erotica and horror stories.

Cognition & emotion·2023

This study evaluates computational models of visual attention using eye-tracking data. It assesses common performance metrics, highlighting their strengths and weaknesses for benchmarking these models.

Area of Science:

  • Cognitive Science
  • Computer Vision
  • Neuroscience

Background:

  • Computational models of visual attention aim to replicate human visual processing.
  • Evaluating these models requires robust and reliable assessment methods.
  • Eye-tracking data offers valuable insights into visual attention patterns.

Purpose of the Study:

  • To review and analyze methods for assessing computational models of visual attention.
  • To identify the strengths and limitations of current performance assessment techniques.
  • To demonstrate the benchmarking of visual attention models using empirical data.

Main Methods:

  • Survey of established performance assessment methods for visual attention models.
  • Analysis of methods utilizing diachronic (time-series) eye-tracking data.

Related Experiment Videos

Last Updated: May 20, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • Empirical benchmarking of selected computational models.

    • Main Results:

    • Common assessment methods for visual attention models were identified and critiqued.
    • Strengths and weaknesses of eye-tracking based evaluation techniques were elucidated.
    • The practical application of these methods for model comparison was demonstrated.

    Conclusions:

    • The choice of assessment method significantly impacts the evaluation of visual attention models.
    • Diachronic eye-tracking data provides a rich basis for model benchmarking.
    • Standardized evaluation protocols are crucial for advancing the field of computational attention modeling.