A Spatio-Temporal Attention-Based Method for Detecting Student Classroom Behaviors
This work addresses the specific issue of student behavior detection in classrooms, which is incremental as it builds on existing methods like SlowFast with attention mechanisms and loss function improvements.
The paper tackles the problem of low accuracy in detecting student behaviors from classroom videos by proposing a spatio-temporal attention-based method (BDSTA), which improves average accuracy by 8.94% compared to the SlowFast model on a self-made dataset.
Accurately detecting student behavior from classroom videos is beneficial for analyzing their classroom status and improving teaching efficiency. However, low accuracy in student classroom behavior detection is a prevalent issue. To address this issue, we propose a Spatio-Temporal Attention-Based Method for Detecting Student Classroom Behaviors (BDSTA). Firstly, the SlowFast network is used to generate motion and environmental information feature maps from the video. Then, the spatio-temporal attention module is applied to the feature maps, including information aggregation, compression and stimulation processes. Subsequently, attention maps in the time, channel and space dimensions are obtained, and multi-label behavior classification is performed based on these attention maps. To solve the long-tail data problem that exists in student classroom behavior datasets, we use an improved focal loss function to assign more weight to the tail class data during training. Experimental results are conducted on a self-made student classroom behavior dataset named STSCB. Compared with the SlowFast model, the average accuracy of student behavior classification detection improves by 8.94\% using BDSTA.