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

Scanpath modeling and classification with hidden Markov models.

Antoine Coutrot1, Janet H Hsiao2, Antoni B Chan3

  • 1CoMPLEX, University College London, London, UK. acoutrot@gmail.com.

Behavior Research Methods
|April 15, 2017
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

Aphantasia is associated with spatial memory and navigation difficulties in complex virtual environments.

Neuropsychologia·2026
Same author

Comparability between AI and human cognition and its role in psychological research and AI ethics.

British journal of psychology (London, England : 1953)·2026
Same author

Reading an Artist's Intention from the Composition (RAIC): eye movements and aesthetic experience in Japanese woodblock prints.

Frontiers in psychology·2025
Same author

Using eye movements, electrodermal activities, and heart rates to predict different types of cognitive load during reading with background music.

Scientific reports·2025
Same author

Education Is Positively and Causally Linked With Spatial Navigation Ability Across the Lifespan.

Open mind : discoveries in cognitive science·2025
Same author

Regional crowd flow estimation from aerial view.

Neural networks : the official journal of the International Neural Network Society·2025
Same journal

Planned missingness in intensive longitudinal studies: Extensions and comparisons of multiform designs.

Behavior research methods·2026
Same journal

A validity-guided workflow for robust large language model research in psychology.

Behavior research methods·2026
Same journal

Are 7-point Likert scales preferable to 5-point scales in language research?

Behavior research methods·2026
Same journal

Generative psychometrics via AI-GENIE: Automatic item generation and validation with network-integrated evaluation.

Behavior research methods·2026
Same journal

Exploring psychological tradeoffs: Developing and demonstrating an R Shiny app for Pareto optimization.

Behavior research methods·2026
Same journal

The performance of Bayesian fit measures in detecting misspecified multilevel structural equation modeling.

Behavior research methods·2026
See all related articles

This study introduces a new method using hidden Markov models (HMMs) and discriminant analysis (DA) to analyze eye movement patterns (scanpaths). This approach accurately infers observer tasks and stimulus characteristics from visual information.

Area of Science:

  • Cognitive Science
  • Computer Science
  • Neuroscience

Background:

  • Scanpath analysis, the study of eye movement sequences, offers insights into observer interests and mental states.
  • Previous methods often used limited gaze descriptors and specialized datasets, hindering broader application.
  • Understanding gaze behavior is crucial for inferring cognitive and perceptual processes.

Purpose of the Study:

  • To develop a comprehensive and adaptable method for scanpath modeling and classification.
  • To infer observer-related characteristics (e.g., task) and stimulus-related characteristics (e.g., content) using eye movement data.
  • To provide a freely available computational toolbox for scanpath analysis.

Main Methods:

  • Utilized variational hidden Markov models (HMMs) to capture dynamic and individual gaze behavior.
Keywords:
ClassificationEye movementsHidden Markov modelsMachine-learningScanpathToolbox

Related Experiment Videos

  • Employed discriminant analysis (DA) to identify systematic patterns in gaze data for classification.
  • Tested the approach on two distinct datasets: static natural scenes and conversational videos.

    • Main Results:

    • Achieved 55.9% accuracy in classifying the task at hand while viewing natural scenes (chance=33%).
    • Achieved 81.2% accuracy in identifying the presence of an original soundtrack in videos (chance=50%).
    • Demonstrated a positive correlation between classification accuracy and the number of salient regions in stimuli.

    Conclusions:

    • The proposed HMM-based method offers a robust approach to scanpath modeling and classification.
    • This synergistic approach integrates behavioral data with machine learning for effective gaze quantification.
    • The released SMAC with HMM toolbox facilitates further research in understanding gaze behavior.