MSTA-SlowFast: A Student Behavior Detector for Classroom Environments

Detecting students' classroom behaviors from instructional videos is important for instructional assessment, analyzing students' learning status, and improving teaching quality. To achieve effective detection of student classroom behavior based on videos, this paper proposes a classroom behavior detection model based on the improved SlowFast. First, a Multi-scale Spatial-Temporal Attention (MSTA) module is added to SlowFast to improve the ability of the model to extract multi-scale spatial and temporal information in the feature maps. Second, Efficient Temporal Attention (ETA) is introduced to make the model more focused on the salient features of the behavior in the temporal domain. Finally, a spatio-temporal-oriented student classroom behavior dataset is constructed. The experimental results show that, compared with SlowFast, our proposed MSTA-SlowFast has a better detection performance with mean average precision (mAP) improvement of 5.63% on the self-made classroom behavior detection dataset.

Automated summary

To effectively detect students' behaviors in the classroom, this study presents a classroom behavior detection model based on an improved SlowFast. The model utilizes a Multi-scale Spatial-Temporal Attention (MSTA) module to extract multi-scale spatial and temporal information, and incorporates Efficient Temporal Attention (ETA) to focus on salient features in the temporal domain. Furthermore, a spatio-temporal-oriented student classroom behavior dataset is constructed. Experimental results demonstrate that our proposed MSTA-SlowFast achieves a better detection performance compared to SlowFast, with a 5.63% improvement in mean average precision (mAP) on the self-made classroom behavior detection dataset.