面向真实课堂的学生行为数据集
Journal: Modern Education Forum DOI: 10.32629/mef.v9i4.20354
Abstract
针对现有课堂行为数据集规模小、视角单一等问题,本文构建了一套来源于真实大学 课堂的大规模学生行为数据集。该数据集包含2282张高分辨率图像和133586个标注 实例,单图平均目标58.54个,并细粒度划分10类典型行为。标注采用“YOLO预标注+人 工修正+双重质检”人机协同闭环机制,标注一致性达到0.85。基于YOLOv8的实验结果 表明,模型在Precision和Recall等指标上均优于现有数据集,在复杂光照和高遮挡场 景下表现出更强的泛化能力,为智慧教育研究提供了可靠的数据支撑。
Keywords
课堂行为识别；数据集构建；高密度场景；多目标检测
Funding
]
Full Text
PDF - Viewed/Downloaded: 4 TimesReferences
[1] LIN L, YANG H, XU Q, et al. Research on student classroom behavior detection based on the real-time detection transfor mer algorithm[J].Applied Sciences,2024;14(14):6153.
[2] HE Q C.Research and implementation of classroom behav ior recognition system for teachers and students based on deep learning[D].Shihezi: Shihezi University,2025.
[3] HAN P C,REN J, SHEN Z P, et al. Overview of deep learning driven automatic classroom behavior recognition technology and method[J].Modern Information Technology,2025;9(20):109 -114.
[4] LIU Q, JIANG X, JIANG R. Classroom behavior recognition using computer vision: A systematic review[J].Sensors,2025;25 (2):373.
[5] GUTTA S,WECHSLER H,PHILLIPS P J.Gender and ethnic cla ssification of face images [C]// Proceedings of the Third IEEE International Conference on Automatic Face and Gesture Rec ognition.Nara,Japan:IEEE,1998:194-199.
[6] LUCEY P,COHN J F,KANADE T,et al.The Extended Cohn- Kanade Dataset (CK+): A complete dataset for action unit and emotion- specified expression [C]// Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. San Francisco,CA,USA:IEEE,2010:94-101.
[7] ZAHARA L,MUSA P, PRASETYO E, et al.The Facial Emotion Recognition(FER- 2013)dataset for prediction system of micro -expressions face using the convolutional neural network CNN algorithm based Raspberry Pi [C]// 2020 Fifth International Conference on Informatics and Computing(ICIC).IEEE,2020:1-9.
[8] JIANG X,ZONG Y,ZHENG W,et al.DFEW:A large-scale datab ase for recognizing dynamic facial expressions in the wild[EB/ OL].https://arxiv.org/abs/2008.05924,2020-08-11.
[9] LI S,DENG W,DU J.Reliable crowdsourcing and deep local ity-preserving learning for expression recognition in the wild [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2017:2852-2861.
[10] LI S, DENG W. Deep Facial Expression Recognition: A Survey[J].IEEE Transactions on Affective Computing,2022,13 (3):1195-1215.
[11] MOLLAHOSSEINI A,HASANI B, MAHOOR M H. AffectNet: A database for facial expression, valence, and arousal computing in the wild[EB/OL].https://arxiv.org/abs/1708.07262, 2017-08- 23.
[12] CARREIRA J,ZISSERMAN A.Quo vadis, action recognition? A new model and the Kinetics dataset[EB/OL].https://arxiv.org/abs /1705.07750,2018-02-22.
[13] DAI J Q,XIE A M, YU D Y. Classroom behavior recognition through joint improvement of Faster RCNN algorithm under the construction of smart education[J].Journal of Digital Conten ts Society,2025,26(2):485-494.
[2] HE Q C.Research and implementation of classroom behav ior recognition system for teachers and students based on deep learning[D].Shihezi: Shihezi University,2025.
[3] HAN P C,REN J, SHEN Z P, et al. Overview of deep learning driven automatic classroom behavior recognition technology and method[J].Modern Information Technology,2025;9(20):109 -114.
[4] LIU Q, JIANG X, JIANG R. Classroom behavior recognition using computer vision: A systematic review[J].Sensors,2025;25 (2):373.
[5] GUTTA S,WECHSLER H,PHILLIPS P J.Gender and ethnic cla ssification of face images [C]// Proceedings of the Third IEEE International Conference on Automatic Face and Gesture Rec ognition.Nara,Japan:IEEE,1998:194-199.
[6] LUCEY P,COHN J F,KANADE T,et al.The Extended Cohn- Kanade Dataset (CK+): A complete dataset for action unit and emotion- specified expression [C]// Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. San Francisco,CA,USA:IEEE,2010:94-101.
[7] ZAHARA L,MUSA P, PRASETYO E, et al.The Facial Emotion Recognition(FER- 2013)dataset for prediction system of micro -expressions face using the convolutional neural network CNN algorithm based Raspberry Pi [C]// 2020 Fifth International Conference on Informatics and Computing(ICIC).IEEE,2020:1-9.
[8] JIANG X,ZONG Y,ZHENG W,et al.DFEW:A large-scale datab ase for recognizing dynamic facial expressions in the wild[EB/ OL].https://arxiv.org/abs/2008.05924,2020-08-11.
[9] LI S,DENG W,DU J.Reliable crowdsourcing and deep local ity-preserving learning for expression recognition in the wild [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2017:2852-2861.
[10] LI S, DENG W. Deep Facial Expression Recognition: A Survey[J].IEEE Transactions on Affective Computing,2022,13 (3):1195-1215.
[11] MOLLAHOSSEINI A,HASANI B, MAHOOR M H. AffectNet: A database for facial expression, valence, and arousal computing in the wild[EB/OL].https://arxiv.org/abs/1708.07262, 2017-08- 23.
[12] CARREIRA J,ZISSERMAN A.Quo vadis, action recognition? A new model and the Kinetics dataset[EB/OL].https://arxiv.org/abs /1705.07750,2018-02-22.
[13] DAI J Q,XIE A M, YU D Y. Classroom behavior recognition through joint improvement of Faster RCNN algorithm under the construction of smart education[J].Journal of Digital Conten ts Society,2025,26(2):485-494.
Copyright © 2026 刘怡萱, 夏永滢, 孟凡爱, 樊荣妍, 张淼
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License