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 Videos

Predicting visual fixations on video based on low-level visual features.

Olivier Le Meur1, Patrick Le Callet, Dominique Barba

  • 1Thomson R&D, 1 Avenue Belle Fontaine, 35511 Cesson-Sevigne, France. olivier.le-meur@thomson.net

Vision Research
|August 11, 2007
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

Multi-Dimensional Quality Assessment for Single-Image-to-3D Contents: Dataset and Model.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Subjective and Objective Audio-Visual Quality Assessment for Omnidirectional Videos.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
Same author

ESIQA: Perceptual Quality Assessment of Vision-Pro-based Egocentric Spatial Images.

IEEE transactions on visualization and computer graphics·2025
Same author

Interactions Between Vibroacoustic Discomfort and Visual Stimuli: Comparison of Real, 3D and 360 Environments.

IEEE transactions on visualization and computer graphics·2025
Same author

Confusing Image Quality Assessment: Toward Better Augmented Reality Experience.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022
Same author

Where to look at the movies: Analyzing visual attention to understand movie editing.

Behavior research methods·2022
Same journal

Editorial for VSI Amblyopia: Advances in Amblyopia Research.

Vision research·2026
Same journal

Computational and mathematical models in vision: Quantitative approaches to understanding visual perception.

Vision research·2026
Same journal

Complex interactions between lightness, chroma, and hue in color ensemble perception.

Vision research·2026
Same journal

Driving with autism spectrum disorder: Exploring the impact of tactile hazard warnings on gaze behavior and hazard responses.

Vision research·2026
Same journal

Early visual processing in adults with ADHD: evidence from contrast sensitivity, spatial integration, and external noise.

Vision research·2026
Same journal

Pupil reflexes generate the peripheral drift illusion due to ON/OFF motion responses.

Vision research·2026
See all related articles

A new computational model accurately predicts visual attention by integrating low-level features like color and motion. This model significantly outperforms existing methods in predicting where observers look in dynamic scenes.

Area of Science:

  • Computational neuroscience
  • Computer vision
  • Human-computer interaction

Background:

  • Understanding visual attention is crucial for fields like AI and user interface design.
  • Existing models often struggle to capture the dynamic interplay of features guiding attention.

Purpose of the Study:

  • To develop and evaluate a novel spatio-temporal computational model of bottom-up visual attention.
  • To assess the predictive power of low-level visual features (achromatic, chromatic, temporal) on attention deployment.
  • To compare the proposed model against established and non-biologically plausible models.

Main Methods:

  • A new spatio-temporal computational model integrating achromatic, chromatic, and temporal saliency maps using a fusion algorithm.
  • Recording eye movements of naive observers viewing natural dynamic scenes.

Related Experiment Videos

  • Quantitative performance assessment using four metrics and comparison with Itti's model and uniform, flicker, and centered models.

    • Main Results:

    • The proposed model demonstrated significant improvements in predicting observer's gaze compared to most benchmarking models.
    • Low-level visual features were shown to have a significant influence on attention deployment over time.
    • The study identified the contribution of temporal dynamics and central bias in eye-tracking experiments.

    Conclusions:

    • The developed model offers a more accurate prediction of visual attention compared to previous models, highlighting the importance of integrating multiple low-level features.
    • Low-level visual features dynamically influence attention, and central bias plays a role in observer behavior.
    • This research contributes to a better understanding of saliency-driven attention and its computational modeling.