Gaze Tracking and Assistive Technology

Optimizing MR-based gaze-decoding for eyes-closed eye-tracking in fMRI

This paper improves gaze decoding in fMRI during eyes-closed states using a deep learning framework, showing it can generalize to eyes-closed conditions with task-specific fine-tuning.

Blinks are strategically coupled with head movements in unconstrained natural gaze behavior

The paper shows blinks are synchronized with head movements to minimize visual input loss during natural gaze behavior.

Single-camera, calibration-free gaze estimation using corneal reflections

This paper introduces a calibration-free corneal-reflection eye tracking system for head-fixed mice using a single camera and multiple fiducial LEDs, achieving sub-degree accuracy and improving receptive field measurements.

Luminance-corrected Pupillometry for Reliable Effort-tracking in Dynamic Environments

This paper introduces a luminance-corrected pupillometry method to improve effort tracking in dynamic environments, showing it enhances discriminability and classification performance when combined with other measures.

NeuroPupil: A generalization-first framework for scalable and biologically informative cross-species pupillometry

NeuroPupil improves cross-species pupillometry with a deep learning framework, achieving better accuracy and efficiency while enabling reliable biological insights.

Characterizing the effect of aging on resting and event-evoked ocular response dynamics

This study examines how aging affects resting and event-evoked ocular responses, finding that pupil dynamics change significantly while microsaccade dynamics remain stable.

Why do we need high-fidelity synthetic eye movement data and how should they look like?

The paper explains the need for high-fidelity synthetic eye movement data and outlines their characteristics, using existing datasets to guide their design and validation.

Eye-Head Coordination During Rapid Gaze Shifts in Soccer Scanning

This study examines eye-head coordination during rapid gaze shifts in soccer players, finding that eye movements primarily drive gaze shifts rather than head movements.

Adaptive Reconstruction of Pupil Dynamics During Blink Data Loss: A Physiologically-Informed Exponential Recovery and Noise Modelling Framework

This paper introduces a framework to reconstruct missing pupil data during blinks using an exponential recovery model and noise estimation, showing improved physiological fidelity compared to traditional methods.

iSleep: Continuous, binocular pupil tracking in sleep and reduced consciousness for physiological monitoring, predictions and interventions

iSleep tracks binocular pupil dynamics during sleep and anesthesia, revealing correlations with brain activity and enabling state prediction and nociception monitoring.

Changes in Ocular Fixation Characteristics Over Time during Reading

This study examines changes in eye fixation characteristics during reading over time, finding that fixation width and intersample distance increase as reading progresses.

Privacy-Preserving Generative AI Framework for Synthetic Multimodal Eye Movement Data

This paper develops a privacy-preserving generative AI framework to create synthetic multimodal eye movement data, which performs comparably to real patient data in clinical tasks.

A Dynamic Threshold-Based Method for Robust and Accurate Blink Detection in Eye-Tracking Data

This paper introduces a dynamic threshold-based blink detection method for eye-tracking data, improving accuracy and robustness across diverse datasets and sampling rates.

Joint infrared pupil images and near-corneal-plane spectral light exposure data under natural conditions across the adult lifespan

The paper presents a dataset of pupil size and spectral light exposure data collected under natural conditions across the adult lifespan to study retinal input variations.

Ocular Response Functions reveal how ocular processes relate to neural activity

The paper models Ocular Response Functions (ORFs) using MEG and eye tracking to reveal neural signatures of oculomotor events and their relationship with neural activity.

Fixation Drift Increases as a Function of Time-on-Task

The paper reports an increase in fixation drift slope over time-on-task in a random saccade task using a large dataset of human subjects.

Deep Learning Detection of Subtle Torsional Eye Movements: Preliminary Results

The paper develops deep learning models to detect torsional eye movements using video-oculography data, achieving 0.9308 AUROC and 86.79% accuracy.

Combining EEG and Eye-Tracking in Virtual Reality - Obtaining Fixation-Onset ERPs and ERSPs

This study combines EEG and eye-tracking in virtual reality to generate fixation-onset ERPs and ERSPs, showing they are less time-sensitive and better suited for naturalistic EEG studies.

Evaluating the validity of the eye movement event detection model of Ganzin Sol glasses

This study evaluates the performance of Ganzin Sol glasses in detecting eye movement events compared to Tobii Pro 2 glasses, finding comparable validity in fixation and saccade tasks.

Web-based eye-tracking for remote cognitive assessments: The anti-saccade task as a case study

This paper presents a web-based eye-tracking prototype for remote cognitive assessments, demonstrating its functionality and limitations using the anti-saccade task.

Quantitative comparison of a mobile, tablet-based and two stationary, video-based eye-trackers

This study compares three eye-trackers, finding differences in performance metrics like saccade latency and gain between the TOM-rm and EL, and noting the TOM-rs matches the EL in high-resolution data.

Continuous Measures of Decision-Difficulty Captured Remotely: II. Webcam eye-tracking reveals early decision processing

This paper uses webcam eye-tracking to measure decision difficulty in binary choice tasks, finding that harder choices involve more eye dwells and longer final dwells.

High-speed MRI recordings of eyeball lifting, retraction and compression during blinks

This study uses high-speed MRI to analyze eye movements during blinks, revealing unexpected lifting, retraction, and compression of the eyeball.

A model of the appearance of the moving human eye

This paper presents a physically accurate model of the human eye's appearance during movement, enabling the estimation of eye pose and biometric parameters from images.

MR-based camera-less eye tracking using deep neural networks

This paper develops DeepMReye, a deep learning model that decodes gaze position from MR signals for camera-less eye tracking in fMRI studies.

New Measures of Visual Scanning Efficiency and Cognitive Effort

The paper introduces new metrics for visual scanning efficiency and cognitive effort using eye tracking data in virtual driving tasks.

EyeLoop: An open-source, high-speed eye-tracker designed for dynamic experiments

EyeLoop is an open-source eye-tracking system enabling dynamic experiments with low-cost hardware, supporting multiple species and closed-loop applications.

Wearable Eye-tracking for Research: Automated dynamic gaze mapping and accuracy/precision comparisons across devices

An automated pipeline maps head-mounted gaze onto a fixed 2D stimulus without tethering participants, plus a task built to compare calibration accuracy and precision across 3 commercial headsets.