基于时空注意力机制的在线教育专注度检测
Engagement Detection Based on Spatio-Temporal Attention Mechanism for Online Education
梁艳 1周卓沂 1黄伟聪 1郭梓健1
作者信息
- 1. 华南师范大学 软件学院,广东 广州 510006
- 折叠
摘要
针对在线教育环境下因时空分离导致教师难以及时获悉学习者专注度的问题,设计一种轻量级深度学习网络模型用于学习者专注度检测.该模型根据学习者的面部表情信息进行决策判断,利用深度残差网络完成空间特征提取,采用长短记忆周期网络完成时序特征提取,并加入空间注意力(SA)和时序注意力(GA)优化模型的特征提取能力,提升专注度检测的效果.实验结果表明,该方法无论在公开数据集还是自采数据集上均获得较高准确率,在精度和时间成本方面能较好地满足实际在线学习场景的需求.
Abstract
Aiming at the problem that it is difficult for teachers to timely learn students'engagement due to the separation of time and space in the online education environment,a lightweight deep learning network model is designed for the detection of students'engagement.The model makes decisions based on the student's facial expression information.It uses a deep residual network to extract spatial features and a long short-term memory network to extract temporal features.The Shuffle Attention and the Global Attention are added to optimize the feature extraction ability of the model to improve the effect of engagement detection.The experimental results show that the proposed method achieves high accuracy on both public and self-collected datasets.It is better suited to the needs of practical online learning scenarios in terms of accu-racy and time cost.
关键词
在线教育/专注度检测/ResNet18/LSTM/注意力机制Key words
online education/engagement detection/ResNet18/LSTM/attention mechanism引用本文复制引用
基金项目
国家科技创新2030"脑科学与类脑智能技术"重点项目(2022ZD0208900)
国家自然科学基金(62076103)
出版年
2024
国家科技期刊平台
NSTL
维普
万方数据