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

Search research articles

Related Experiment Video

Updated: Jul 12, 2025

Using Electroencephalography Measurements and High-quality Video Recording for Analyzing Visual Perception of Media Content

Using Electroencephalography Measurements and High-quality Video Recording for Analyzing Visual Perception of Media Content

Published on: May 26, 2018

BlinkLinMulT: Transformer-Based Eye Blink Detection.

Ádám Fodor¹, Kristian Fenech¹, András Lőrincz¹

¹Department of Artificial Intelligence, Eötvös Loránd University, Pázmány Péter stny 1/A, 1117 Budapest, Hungary.

Journal of Imaging

|October 27, 2023

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

Cross-Viewpoint Semantic Mapping: Integrating Human and Robot Perspectives for Improved 3D Semantic Reconstruction.

Sensors (Basel, Switzerland)·2023

Same author

Peripheral gene interactions define interpretable clusters of core ASD genes in a network-based investigation of the omnigenic theory.

NPJ systems biology and applications·2022

Same author

Tracking Highly Similar Rat Instances under Heavy Occlusions: An Unsupervised Deep Generative Pipeline.

Journal of imaging·2022

Same journal

Human-AI Interaction in Interventional Radiology: A Narrative Review of Current Applications, Challenges, and Future Directions.

Journal of imaging·2026

Same journal

Coronary Artery Anomalies and Anatomical Variants: Cross-Sectional Diagnostic Imaging and Clinical Background.

Journal of imaging·2026

Same journal

YoLeTooth: A Unified Framework for Joint Tooth Segmentation and Periapical Lesion Detection in Panoramic Radiographs.

Journal of imaging·2026

Same journal

Radiomics-Guided Multi-Sequence Learning for Pathological Complete Response Prediction from Breast MRI with Missing Auxiliary Sequences.

Journal of imaging·2026

Same journal

Cutaneous Thermography in Arthropathies: Quantitative Imaging, Machine Learning, and Clinical Translation.

Journal of imaging·2026

Same journal

Two-Stage Dynamic Synergistic Segmentation Method for Myocardial Pathology.

Journal of imaging·2026

See all related articles

This study introduces BlinkLinMulT, a novel transformer framework for accurate eye blink detection. It outperforms existing methods by efficiently fusing features and using linear attention, showing strong performance across diverse datasets.

Area of Science:

Computer Vision
Machine Learning
Biomedical Signal Processing

Background:

Existing eye blink detection methods often rely on frame-wise classification.
Transformer-based sequence models offer advanced capabilities not yet explored in blink detection.
Challenges include varying lighting conditions and diverse head poses.

Purpose of the Study:

Introduce BlinkLinMulT, a transformer-based framework for eye blink detection.
Leverage transformer architecture for blink presence and eye state recognition.
Develop an efficient feature fusion method for improved accuracy.

Main Methods:

Utilized a transformer-based framework (BlinkLinMulT).
Combined low- and high-level feature sequences.

Keywords:

classification deep learning eye blink detection multimodal fusion transformers

More Related Videos

Classical Short-Delay Eyeblink Conditioning in One-Year-Old Children

Classical Short-Delay Eyeblink Conditioning in One-Year-Old Children

Published on: September 1, 2018

Whisker-signaled Eyeblink Classical Conditioning in Head-fixed Mice

Whisker-signaled Eyeblink Classical Conditioning in Head-fixed Mice

Published on: March 30, 2016

Related Experiment Videos

Last Updated: Jul 12, 2025

Using Electroencephalography Measurements and High-quality Video Recording for Analyzing Visual Perception of Media Content

Using Electroencephalography Measurements and High-quality Video Recording for Analyzing Visual Perception of Media Content

Published on: May 26, 2018

Classical Short-Delay Eyeblink Conditioning in One-Year-Old Children

Classical Short-Delay Eyeblink Conditioning in One-Year-Old Children

Published on: September 1, 2018

Whisker-signaled Eyeblink Classical Conditioning in Head-fixed Mice

Whisker-signaled Eyeblink Classical Conditioning in Head-fixed Mice

Published on: March 30, 2016

Implemented linear complexity cross-modal attention mechanisms.

Efficiently fused input features.

Main Results:

Achieved state-of-the-art performance in eye blink detection.
Demonstrated strong generalization capability across multiple benchmark datasets (CEW, ZJU, MRL Eye, RT-BENE, EyeBlink8, Researcher's Night, TalkingFace).
Successfully addressed challenges like lighting changes and varied head poses.

Conclusions:

BlinkLinMulT establishes a new baseline for eye blink detection research.
The transformer architecture is effective for blink detection and eye state recognition.
Efficient feature fusion enhances model performance and robustness.