GazeBase Data Repository

GazeBase is a large-scale longitudinal dataset consisting of 12,334 monocular (left) eye-movement recordings captured from 322 college-aged subjects. Subjects completed a battery of seven tasks in two adjacent sessions during each round of recording, including a - 1) fixation task, 2) horizontal saccade task, 3) random oblique saccade task, 4) reading task, 5/6) free viewing of cinematic video task, and 7) gaze-driven gaming task. A total of nine rounds of recording were conducted over a 37 month period, with participants in each subsequent round recruited exclusively from prior rounds. All data was collected using an EyeLink 1000 eye tracker at a 1,000 Hz sampling rate, with a calibration and validation protocol performed before each task to ensure data quality. Due to its large number of participants and longitudinal nature, GazeBase is well suited for exploring research hypotheses in eye movement biometrics, along with other emerging applications applying machine learning techniques to eye movement signal analysis. Eye movement classification labels produced by the instrument's real-time parser are provided for a relevant subset of GazeBase, along with pupil area. Full details regarding the experimental protocol are available in the corresponding data descriptor manuscript.

GazeBase是一款大规模纵向数据集（longitudinal dataset），涵盖从322名青年大学生受试者身上采集的12334条单眼（左眼）眼动记录（eye-movement recordings）。受试者在每一轮数据采集周期内，需在相邻的两个会话中完成一套包含7项任务的测验组合，具体包括：1）固视任务（fixation task）、2）水平眼跳任务（horizontal saccade task）、3）随机斜向眼跳任务（random oblique saccade task）、4）阅读任务（reading task）、5/6）电影视频自由观看任务（free viewing of cinematic video task），以及7）眼动驱动游戏任务（gaze-driven gaming task）。该数据集在37个月的周期内共完成9轮数据采集，后续每一轮的招募对象均仅来自此前各轮的参与者。所有数据均采用EyeLink 1000眼动仪以1000Hz的采样率采集，且每项任务实施前均会执行校准与验证流程以保障数据质量。依托庞大的受试者规模与纵向研究特性，GazeBase非常适合用于探索眼动生物特征识别（eye movement biometrics）领域的研究假说，以及其他将机器学习技术应用于眼动信号分析的新兴研究场景。数据集为GazeBase的相关子集提供了由仪器实时解析器生成的眼动分类标签，同时附带瞳孔面积数据。有关实验流程的完整细节可参阅对应的数据集描述研究手稿。

搜集汇总

背景与挑战

背景概述

GazeBase是一个大规模纵向眼动数据集，包含322名大学生的12,334次单眼眼动记录，覆盖七项任务和37个月的记录周期。数据使用EyeLink 1000眼动仪以1,000 Hz采样率收集，适用于眼动生物识别和机器学习应用。