IREYE4TASK

IREYE4TASK is a dataset for wearable eye landmark detection and mental state analysis. Sensing the mental state induced by different task contexts, where cognition is a focus, is as important as sensing the affective state where emotion is induced in the foreground of consciousness, because completing tasks is part of every waking moment of life. However, few datasets are publicly available to advance mental state analysis, especially those using the eye as the sensing modality with detailed ground truth for eye behaviors. Here, we share a high-quality publicly accessible eye video dataset, IREye4Task, where the eyelid, pupil and iris boundary as well as six eye states, four mental states in two load levels, and before and after experiment are annotated for each frame to obtain eye behaviors as responses to different task contexts, over more than a million frames. This dataset provides an opportunity to recognize eye behaviors from close-up infrared eye images and examine the relationship between eye behaviors, different mental states and task performance.IREYE4TASK是一款面向可穿戴眼部地标检测与心理状态分析的数据集。感知不同任务情境诱发的心理状态（核心研究对象为认知活动），与感知意识表层由情绪引发的情感状态同等重要，因为完成任务是人类清醒时段的日常组成部分。然而，当前用于推动心理状态分析研究的公开数据集仍较为稀缺，尤其是以眼部作为感知模态、并附带眼部行为详细真实标注的数据集更是屈指可数。本次我们公开分享一款高质量可获取的眼部视频数据集IREye4Task，其总帧数超过百万，每帧均完成以下标注：眼睑、瞳孔与虹膜边界，六种眼部状态，两种任务负荷水平下的四种心理状态，以及实验前后的相关状态，以此提取对应不同任务情境的眼部行为响应特征。该数据集为从近距离红外眼部影像中识别眼部行为，以及探究眼部行为、不同心理状态与任务绩效之间的内在关联提供了重要研究契机。

搜集汇总

背景与挑战

背景概述

IREYE4TASK是一个高质量的红外眼动视频数据集，专注于可穿戴眼动地标检测和心智状态分析。它包含超过一百万帧的标注数据，涵盖眼睑、瞳孔、虹膜边界、六种眼动状态和四种心智状态（两种负载水平），适用于研究眼动行为与任务表现及心智状态之间的关联。数据集基于20名参与者的实验，设计包括认知、感知、身体和沟通四种任务类型，并提供详细的地标和状态注释，支持眼动行为分析和机器学习应用。