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

Construction of Individual Morphological Brain Networks with Multiple Morphometric Features.

Frontiers in neuroanatomy·2017
Same author

N-Monomethylation of amines using paraformaldehyde and H<sub>2</sub>.

Chemical communications (Cambridge, England)·2017
Same author

Isointense Infant Brain Segmentation by Stacked Kernel Canonical Correlation Analysis.

Patch-based techniques in medical imaging : First International Workshop, Patch-MI 2015, held in conjunction with MICCAI 2015, Munich, Germany, October 9, 2015, revised selected papers. Patch-MI (Workshop) (1st : 2015 : Munich, Germany)·2017
Same author

Diffuse lesion and necrosis tied to poorer prognosis of interdigitating dendritic cell sarcoma: cases report and a pooled analysis.

Scientific reports·2017
Same author

Protein Regulator of Cytokinesis PRC1 Confers Chemoresistance and Predicts an Unfavorable Postoperative Survival of Hepatocellular Carcinoma Patients.

Journal of Cancer·2017
Same author

Comparison of degradation and recaesiation between GaAs and AlGaAs photocathodes in an unbaked vacuum system.

Applied optics·2017

Related Experiment Video

Updated: Jul 31, 2025

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

442

EM-Gaze: eye context correlation and metric learning for gaze estimation.

Jinchao Zhou1, Guoan Li1, Feng Shi2

  • 1State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, 100191, China.

Visual Computing for Industry, Biomedicine, and Art
|May 5, 2023
PubMed
Summary

This study introduces an efficient deep neural network for accurate 2D gaze estimation on mobile devices. The novel method enhances both gaze point accuracy and classification performance, outperforming existing techniques.

Keywords:
AttentionComputer visionGaze estimationMetric learningMulti-task 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
Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

10.7K

Related Experiment Videos

Last Updated: Jul 31, 2025

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

442
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
Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

10.7K

Area of Science:

  • Computer Vision
  • Human-Computer Interaction
  • Machine Learning

Background:

  • Gaze estimation is crucial for computer vision and human-computer interaction.
  • Previous research focused on 2D/3D gaze prediction from single face images.
  • Mobile gaze estimation presents unique challenges due to computational constraints.

Purpose of the Study:

  • To develop a deep neural network for efficient 2D gaze estimation on mobile devices.
  • To improve both gaze point regression accuracy and quadrant classification performance.
  • To achieve state-of-the-art results on benchmark datasets.

Main Methods:

  • Proposed an efficient attention-based module to correlate and fuse eye features.
  • Integrated metric learning for gaze classification on display quadrants.
  • Utilized a unified perspective for gaze estimation, combining regression and classification.

Main Results:

  • Achieved state-of-the-art 2D gaze point regression error.
  • Significantly improved gaze classification error on quadrant divisions.
  • Demonstrated superior performance compared to existing methods on GazeCapture and MPIIFaceGaze datasets.

Conclusions:

  • The proposed deep neural network effectively enhances mobile 2D gaze estimation.
  • The attention-based module and metric learning contribute to improved accuracy.
  • The method offers a promising solution for real-world gaze tracking applications.