Abstract: Highlights•A student dataset is formed with annotated videos for students actions and engagement.•PoseConv3D model is finetuned to detect student’s actions using upper body joints.•A novel histogram-based approach is proposed to measure student behavioral engagement.•Disengaged samples are increased through synthesizing using kernel density estimate.
External IDs:dblp:journals/prl/AbdelkawyFAAFTH24
Loading