mEBAL眨眼与注意力数据集
多模态RGB/NIR眼部序列，用于眨眼检测和注意力估计，由BiDAlab提供，来自GitHub数据库，包含342000条数据，适用于分类任务。
基本信息
资源简介
mEBAL眨眼与注意力数据集
【数据集背景】
本数据集源站标题为《BiDAlab/mEBAL》。源站首次发布：2020-06-09。
【数据内容】
源站原始描述：mEBAL is a multimodal database for eye blink detection and attention level estimation. *** # About We present mEBAL [1], a multimodal database for eye blink detection and attention level estimation. mEBAL is a database which is initially introduced in arXiv technical report and then accepted by the 22nd ACM International Conference on Multimodal Interaction. 📢 **Update: New Version Released – mEBAL2:** A new version of this database, mEBAL2, has been released and is available on GitHub at the fo…
【主题与分类】
主题标签：attention-level、cognitive-modelling、e-learning、eye-blink、eye-blink-detection。
【适用方向】
多模态数据适合跨模态对齐、融合建模与联合表征学习方向的研究。
【获取与许可】
源站页面：https://github.com/BiDAlab/mEBAL
【使用注意】
· 源站最后修改于 2025-05-13，引用时请注意版本时效。
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载，适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档，适合快速预览和评估数据集质量。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务（收技术服务费，非数据销售）
暂未开放当前数据集主要来源为 Kaggle 公开托管，完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取
git clone https://github.com/BiDAlab/mEBAL.git
curl -L -o repo.zip https://github.com/BiDAlab/mEBAL/archive/refs/heads/master.zip
unzip repo.zip
源站 README 摘录（使用方式）
About
We present mEBAL [1], a multimodal database for eye blink detection and attention level estimation. mEBAL is a database which is initially introduced in arXiv technical report and then accepted by the 22nd ACM International Conference on Multimodal Interaction.
📢 Update: New Version Released – mEBAL2: A new version of this database, mEBAL2, has been released and is available on GitHub at the following link. It includes an expanded dataset with 10,550 eyeblinks and 10,550 no-blink events, along with a more diverse group of users, consisting of 180 different students.
The eye blink frequency is related to the cognitive activity and automatic detectors of eye blinks have been proposed for many tasks including attention level estimation, analysis of neuro-degenerative diseases, deception recognition, drive fatigue detection, or face anti-spoofing. However, most existing databases and algorithms in this area are limited to experiments involving only a few hundred samples and individual sensors like face cameras.
The proposed mEBAL improves previous databases in terms of numbers samples in eye blink and cognitive information available. In particular, three different sensors are simultaneously considered: Near Infrared (NIR) and RGB cameras to capture the face gestures and an Electroencephalography (EEG) band to capture the cognitive activity of the user and blinking events.
Regarding the size of mEBAL, it comprises 3,000 blink samples and the corresponding attention level from 38 different students while conducting a number of e-learning tasks of varying difficulty. This information is avalible on this web [Download Database].
The following table summarises the demographic distribution of the 38 participants in the mEBAL dataset.
<h3 align=“center”>Distribution of Learners by Gender, Age, and Glasses Usage</h3>
<div align=“center”>
<table>
<thead>
<tr>
<th>Category</th>
<th>Subcategory</th>
<th>Percentage</th>
<th>Number of Learners</th>
<th>Average Age</th>
<tbody>
<tr><td>Gender</td><td>Male</td><td>81.58%</td><td>31</td><td>25.0645</td></tr>
<tr><td></td><td>Female</td><td>18.42%</td><td>7</td><td>23.7143</td></tr>
<tr><
数据加载示例（表格/文本类）
import pandas as pd, glob, os
files = (glob.glob(os.path.join(path, "**", "*.csv"), recursive=True)
+ glob.glob(os.path.join(path, "**", "*.tsv"), recursive=True)
+ glob.glob(os.path.join(path, "**", "*.xlsx"), recursive=True))
print("数据文件:", files)
df = pd.read_csv(files[0])
print(df.shape); print(df.columns.tolist()); print(df.head(3))
数据缺失？
依托陕西、四川两大基地，我们与超过十家三甲医院建立直接合作关系，覆盖合规授权、采集治理、专业标注、数据交付的全流程，为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务？立即联系我们获取专业方案。
