Exploring the Application of Visual Question Answering (VQA) for Classroom Activity Monitoring

TL;DR

This study evaluates the effectiveness of state-of-the-art VQA models in analyzing classroom behavior from video recordings, introducing a new dataset and benchmarking their performance for educational monitoring applications.

Contribution

It introduces the BAV-Classroom-VQA dataset and benchmarks multiple VQA models for classroom behavior analysis, advancing AI tools in educational research.

Findings

All models achieved promising performance levels.

VQA models show potential for classroom analytics.

Dataset facilitates rigorous evaluation of VQA in education.

Abstract

Classroom behavior monitoring is a critical aspect of educational research, with significant implications for student engagement and learning outcomes. Recent advancements in Visual Question Answering (VQA) models offer promising tools for automatically analyzing complex classroom interactions from video recordings. In this paper, we investigate the applicability of several state-of-the-art open-source VQA models, including LLaMA2, LLaMA3, QWEN3, and NVILA, in the context of classroom behavior analysis. To facilitate rigorous evaluation, we introduce our BAV-Classroom-VQA dataset derived from real-world classroom video recordings at the Banking Academy of Vietnam. We present the methodology for data collection, annotation, and benchmark the performance of the selected VQA models on this dataset. Our initial experimental results demonstrate that all four models achieve promising performance levels in answering behavior-related visual questions, showcasing their potential in future classroom analytics and intervention systems.