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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Accelerating responsibly: From novelty to necessity in visual assistive technology.

Assistive technology : the official journal of RESNA·2026
Same author

PALMS+: Modular Image-Based Floor Plan Localization Leveraging Depth Foundation Model.

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision·2026
Same author

Connecting the dots: addressing lipid emulsion substitution risks in local anesthetic systemic toxicity.

Regional anesthesia and pain medicine·2026
Same author

VI-OCR: "Visually Impaired" optical character recognition pipeline for text accessibility assessment.

Scientific reports·2025
Same author

Beyond fiberoptic: securing the airway in a child with bilateral TMJ ankylosis.

Journal of dental anesthesia and pain medicine·2025
Same author

An Approach to Intraoperative Accidental Pulmonary Artery Transection and Role of Mid-Point to Transverse Process Interfascial Plane Block.

Annals of cardiac anaesthesia·2025
Same journal

Towards the Efficient Inference by Incorporating Automated Computational Phenotypes under Covariate Shift.

Proceedings of machine learning research·2026
Same journal

Endo-SemiS: Towards Robust Semi-Supervised Image Segmentation for Endoscopic Video.

Proceedings of machine learning research·2026
Same journal

Perspective: Machine Learning for Health Should Consider Social Drivers of Health.

Proceedings of machine learning research·2026
Same journal

Classifying Phonotrauma Severity from Vocal Fold Images with Soft Ordinal Regression.

Proceedings of machine learning research·2026
Same journal

Does Domain-Specific Retrieval Augmented Generation Help LLMs Answer Consumer Health Questions?

Proceedings of machine learning research·2026
Same journal

Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential.

Proceedings of machine learning research·2026
See all related articles

Related Experiment Video

Updated: Jul 26, 2025

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

466

Contrastive Representation Learning for Gaze Estimation.

Swati Jindal1, Roberto Manduchi1

  • 1University of California, Santa Cruz, Santa Cruz, CA, 95064, USA.

Proceedings of Machine Learning Research
|June 16, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces Gaze Contrastive Learning (GazeCLR), a new self-supervised learning method for gaze estimation. GazeCLR enhances representation learning for improved accuracy, especially in cross-domain scenarios.

Keywords:
gaze estimationrepresentation learningself-supervised learning

More Related Videos

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
09:27

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

10.1K
Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects
07:36

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects

Published on: November 30, 2018

15.8K

Related Experiment Videos

Last Updated: Jul 26, 2025

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

466
Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
09:27

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

10.1K
Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects
07:36

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects

Published on: November 30, 2018

15.8K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Human-Computer Interaction

Background:

  • Self-supervised learning (SSL) commonly uses contrastive learning for visual representation, focusing on invariance to image transformations.
  • Gaze estimation requires both appearance invariance and geometric transformation equivariance, which traditional SSL methods may not fully address.

Purpose of the Study:

  • To propose Gaze Contrastive Learning (GazeCLR), a novel SSL framework tailored for gaze estimation.
  • To develop a method that promotes both invariance and equivariance in visual representations for gaze direction.

Main Methods:

  • GazeCLR utilizes multi-view data to enforce equivariance to geometric transformations.
  • Specific data augmentation techniques are employed to maintain invariance to appearance changes without altering gaze direction.

Main Results:

  • GazeCLR demonstrates significant effectiveness across various gaze estimation tasks.
  • The framework achieves up to 17.2% relative improvement in cross-domain gaze estimation.
  • GazeCLR shows competitive performance against state-of-the-art methods in few-shot evaluation.

Conclusions:

  • GazeCLR offers a simple yet effective contrastive representation learning approach for gaze estimation.
  • The method successfully balances invariance and equivariance, outperforming existing techniques in challenging scenarios.
  • The proposed framework advances the field of gaze estimation through improved representation learning.