A Dynamic Position Embedding-Based Model for Student Classroom Complete Meta-Action Recognition

Abstract

The precise recognition of entire classroom meta-actions is a crucial challenge for the tailored adaptive interpretation of student behavior, given the intricacy of these actions. This paper proposes a Dynamic Position Embedding-based Model for Student Classroom Complete Meta-Action Recognition (DPE-SAR) based on the Video Swin Transformer. The model utilizes a dynamic positional embedding technique to perform conditional positional encoding. Additionally, it incorporates a deep convolutional network to improve the parsing ability of the spatial structure of meta-actions. The full attention mechanism of ViT3D is used to extract the potential spatial features of actions and capture the global spatial–temporal information of meta-actions. The proposed model exhibits exceptional performance compared to baseline models in action recognition as observed in evaluations on public datasets and smart classroom meta-action recognition datasets. The experimental results confirm the superiority of the model in meta-action recognition.

Keywords

• meta-action recognition
• Video Swin Transformer
• dynamic positional embedding
• ViT3D