Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

OCT-Based Retina Assessment Reflects Visual Impairment in Multiple Sclerosis.

Investigative ophthalmology & visual science·2025

Same author

Using Hierarchical Bayesian Modeling to Enhance Statistical Inference on Contrast Sensitivity.

Translational vision science & technology·2024

Same author

Quantifying the Functional Relationship Between Visual Acuity and Contrast Sensitivity Function.

Investigative ophthalmology & visual science·2024

Same author

Predicting contrast sensitivity functions with digital twins.

Scientific reports·2024

Same author

Quantification of expected information gain in visual acuity and contrast sensitivity tests.

Scientific reports·2023

Same author

Visual function resists early neurodegeneration in the visual system in primary progressive multiple sclerosis.

Journal of neurology, neurosurgery, and psychiatry·2023

Search research articles

Related Experiment Video

Updated: May 20, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Eye movement prediction and variability on natural video data sets.

Michael Dorr¹, Eleonora Vig, Erhardt Barth

¹Institute for Neuro- and Bioinformatics, University of Lübeck, Ratzeburger Allee 160, D-23538 Lübeck, Germany, vig@inb.uni-luebeck.de , barth@inb.uni-luebeck.de.

Visual Cognition

|July 31, 2012

Summary

Researchers studied eye movement predictability in natural videos. A novel saliency model integrating structure tensor invariants and machine learning outperformed existing methods, offering insights into gaze behavior and video saliency.

More Related Videos

Using Eye-tracking to Assess the Relative Importance of Visual and Vestibular Input to Subcortical Motion Processing in the Roll Plane

Using Eye-tracking to Assess the Relative Importance of Visual and Vestibular Input to Subcortical Motion Processing in the Roll Plane

Published on: August 22, 2025

Loneliness Assuaged: Eye-Tracking an Audience Watching Barrage Videos

Loneliness Assuaged: Eye-Tracking an Audience Watching Barrage Videos

Published on: May 29, 2020

Related Experiment Videos

Last Updated: May 20, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Using Eye-tracking to Assess the Relative Importance of Visual and Vestibular Input to Subcortical Motion Processing in the Roll Plane

Using Eye-tracking to Assess the Relative Importance of Visual and Vestibular Input to Subcortical Motion Processing in the Roll Plane

Published on: August 22, 2025

Loneliness Assuaged: Eye-Tracking an Audience Watching Barrage Videos

Loneliness Assuaged: Eye-Tracking an Audience Watching Barrage Videos

Published on: May 29, 2020

Area of Science:

Computer Vision
Neuroscience
Human-Computer Interaction

Background:

Eye movements are crucial for visual information processing.
Predicting gaze patterns in videos is challenging due to complex visual content.
Existing saliency models vary in effectiveness across different video types.

Purpose of the Study:

To evaluate the predictability of eye movements during natural high-resolution video viewing.
To compare the performance of state-of-the-art saliency models on diverse video datasets.
To investigate the relationship between gaze variability, predictability, and video characteristics.

Main Methods:

Utilized three distinct gaze datasets encompassing various video genres (still-life, advertisements, movie trailers).
Assessed three contemporary saliency models, including a novel approach based on structure tensor invariants and machine learning.
Extended the best-performing model with a perceptually inspired color space for further evaluation.

Main Results:

Inter-subject gaze variability differed significantly across datasets, being lowest for professional movies.
The structure tensor-based saliency model demonstrated superior performance compared to reference models.
Model performance improved with the addition of a perceptually inspired color space on two datasets.
Eye movements on professional movies were coherent but less predictable due to frequent scene changes.

Conclusions:

The developed saliency model shows promise for predicting eye movements in natural videos.
Gaze guidance strategies in professional filmmaking influence eye movement coherence and predictability.
Standardized benchmarks are essential for robust evaluation of eye movement prediction algorithms.