Eye Tracking
Overview
Eye tracking uses cameras and other sensors to estimate gaze direction and characterize movements such as fixations and saccades, revealing how people explore visual information. Methods include geometric pupil-and-glint models, appearance-based deep learning, temporal sequence models, and calibration or synthetic-data techniques for adapting systems to users and devices. Applications range from reading, visual search, and clinical assessment to driving, robotics, and interactive displays. A central challenge is making systems accurate beyond controlled settings, where lighting, motion, device placement, and individual differences increase error and calibration demands; behavioral or clinical conclusions also require careful validation.
Latest papers
65 papers6 papers in the last four weeks, up 50% on the four weeks before. 0.0% of all new papers.
Characterizing Scanpath Decoding Pipelines with Perturbation Profiles
How Well Does Webcam Eye Tracking Work "in the Wild"? A Large-Scale Validation of Chiasm and a Comparison with WebGazer
Evaluating Visual Realism of AI-Generated Videos with Eye Tracking
Predicting Individual Differences in Lipreading From Eye-Tracking and Pupillometry During Silent Visual Speech
GazeAgent: VLM-Guided Implicit Gaze Calibration from Egocentric Multimodal Behavior for AI Glasses
Task-evoked eye movements as candidate digital biomarkers of depression severity in adolescents and young adults
From Laboratory to Road: Evaluating Wearable Gaze Accuracy for Driving
A Biomimetic Gaze Control to Restore Head-Neck Movements
Eyes on the Road: A Naturalistic Comparison of MTW Rider Gaze in Urban Indian Traffic
Low Cost Eye Tracking for Vision Screening
Marker-free eye-gaze estimation using a single image and depth from defocus
GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History
Diffusion models for eye-gaze trajectory generation using position and velocity representations
An Intelligent Decision Support System for Emotion Monitoring using Microscopic Fixational Dynamics
Language Proficiency Assessment from Eye Movements in Naturalistic Passage Reading
Drift Calibration in Geometric Eye Tracking Systems
AOI-Net: Structural Face AOI-Guided Eye-Gaze Track Representation Learning for Autism Spectrum Disorder Detection
A Hybrid Gaze-Motor Imagery BCI Framework for Effective Decision Communication
Measuring Browser Webcam Gaze Honestly: A Capture-Clock Methodology and Open Reference Implementation
re\-quest\-Video\-Frame\-Call\-back (rVFC) API (captureTime where the browser exposes it for local camera streams, else presentationTime, in which case every recovered latency is a verifiable lower bound): exact source-frame pairing through a per-frame queue for engines that expose their inference pipeline, and a further lower bound for engines that do not, such as WebGazer. We release an open TypeScript implementation and benchmark harness, demonstrated on two interchangeable engines: WebGazer and a new FaceMesh+KRR pipeline.