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: Dec 9, 2025

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

8.0K

Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset.

Ruohan Zhang1, Calen Walshe2, Zhuode Liu1

  • 1Department of Computer Science, University of Texas at Austin.

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence
|September 9, 2020
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

Identification of WRKY transcription factors (TFs) in the recretohalophyte Tamarix chinensis and functional analysis of TcWRKY13 under salt stress.

Plant cell reports·2026
Same author

Sex differences in activations to the sight of faces, scenes, body parts and tools in visual and non-visual cortical regions leading to the human hippocampus.

Biology of sex differences·2026
Same author

A multi-centre, prospective trial of a methylation-based liquid biopsy for early detection of liver cancer in high-risk populations.

Clinical and translational medicine·2026
Same author

Cudratricusxanthone A Exhibits Antitumor Activities Against NSCLC Harboring EGFR L792H and G796R Triple Mutations via Regulating EGFR-ERK/AKT/STAT3 Signaling.

Molecules (Basel, Switzerland)·2026
Same author

Affective responses during low-volume high-intensity interval exercise in overweight and obese adults: A systematic review.

Sports medicine and health science·2026
Same author

Ultra-narrowband perovskite single-crystal photodetector enabled by dynamic space charge region for portable concentration detection.

Science advances·2026
Same journal

Interpretable Failure Detection with Human-Level Concepts.

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence·2026
Same journal

ChatCLIDS: Simulating Persuasive AI Dialogues to Promote Closed-Loop Insulin Adoption in Type 1 Diabetes Care.

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence·2026
Same journal

Beyond Accuracy: On the Effects of Fine-tuning Towards Vision-Language Model's Prediction Rationality.

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence·2026
Same journal

<i>OrgaCast</i>: A Trustworthy Spatiotemporal Diffusion Model for Fluorescence Organoid Forecasting.

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence·2026
Same journal

Apo2Mol: 3D Molecule Generation via Dynamic Pocket-Aware Diffusion Models.

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence·2026
Same journal

iDT-diet: Toward Personalized Health Forecasting-An Intelligent Digital Twin Model for Diet-Influenced Biomarker Trajectories (Student Abstract).

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence·2026
See all related articles

This study introduces a large dataset of human gameplay and eye movements for AI research. Incorporating visual attention models significantly boosts AI performance in decision-making tasks.

Area of Science:

  • Artificial Intelligence
  • Cognitive Science
  • Human-Computer Interaction

Background:

  • High-quality datasets are crucial benchmarks for advancing AI decision-making research.
  • Human decision-making often relies on visual attention, making eye-movement data valuable for understanding strategies.
  • Existing datasets may not fully capture the nuances of human visual attention during complex tasks.

Purpose of the Study:

  • To introduce a large-scale, high-quality dataset of human actions and simultaneous eye movements during Atari gameplay.
  • To provide a benchmark for developing and evaluating AI methods in decision-making, visual attention, and imitation learning.
  • To demonstrate the utility of the dataset for predicting human gaze and improving imitation learning.

Main Methods:

More Related Videos

Eye Tracking Young Children with Autism
09:03

Eye Tracking Young Children with Autism

Published on: March 27, 2012

46.2K
Eye Tracking During A Complex Aviation Task For Insights Into Information Processing
07:48

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

997

Related Experiment Videos

Last Updated: Dec 9, 2025

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

8.0K
Eye Tracking Young Children with Autism
09:03

Eye Tracking Young Children with Autism

Published on: March 27, 2012

46.2K
Eye Tracking During A Complex Aviation Task For Insights Into Information Processing
07:48

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

997
  • Collected 117 hours of gameplay data across 20 Atari games, featuring 8 million action demonstrations and 328 million gaze samples.
  • Developed a novel semi-frame-by-frame gameplay method to elicit near-optimal human decisions.
  • Utilized the dataset to train models for predicting human gaze and for imitation learning.

    • Main Results:

    • The dataset comprises extensive human gameplay and eye-tracking data, enabling reproducible AI research.
    • Predicting human gaze and imitating demonstrated actions yielded promising results using the new dataset.
    • Integrating a learned human gaze model into imitation learning improved game performance by 115%.

    Conclusions:

    • The dataset's scale and quality underscore the importance of human visual attention in AI decision-making models.
    • This resource offers significant opportunities for researchers in visual attention, imitation learning, and reinforcement learning.
    • Incorporating insights from human visual strategies can substantially enhance AI agent performance.