ARIC: An Activity Recognition Dataset in Classroom Surveillance Images

2024-10-16

arXiv.org

AI Summary

Existing classroom activity recognition research relies heavily on manually captured videos, offers limited activity categories, and overlooks critical challenges in real-world surveillance settings—namely, severe class imbalance and high inter-class similarity. To address these issues, we propose ARIC, the first multimodal activity recognition benchmark tailored for authentic classroom surveillance. ARIC comprises 32 pedagogically meaningful activity classes, synchronized RGB, thermal, and skeleton modalities, and multi-view recordings. It introduces scene-driven annotation, a continual learning protocol, and a meta few-shot split to systematically tackle class skew and fine-grained discrimination. ARIC supports three core tasks: standard activity recognition, continual learning, and few-shot continual learning. The dataset is publicly released and has been adopted by multiple educational AI research teams. By establishing a realistic, scalable, and rigorously structured benchmark, ARIC provides a foundational resource and a new paradigm for open-ended teaching scene analysis.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Active Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements

Abstract

The application of activity recognition in the ``AI + Education"field is gaining increasing attention. However, current work mainly focuses on the recognition of activities in manually captured videos and a limited number of activity types, with little attention given to recognizing activities in surveillance images from real classrooms. Activity recognition in classroom surveillance images faces multiple challenges, such as class imbalance and high activity similarity. To address this gap, we constructed a novel multimodal dataset focused on classroom surveillance image activity recognition called ARIC (Activity Recognition In Classroom). The ARIC dataset has advantages of multiple perspectives, 32 activity categories, three modalities, and real-world classroom scenarios. In addition to the general activity recognition tasks, we also provide settings for continual learning and few-shot continual learning. We hope that the ARIC dataset can act as a facilitator for future analysis and research for open teaching scenarios. You can download preliminary data from https://ivipclab.github.io/publication_ARIC/ARIC.

Problem

• Recognize activities in classroom surveillance images
• Address class imbalance and high activity similarity
• Provide dataset for continual and few-shot learning

Innovation

• Multimodal dataset for classroom activity recognition
• Includes 32 activity categories and real-world scenarios
• Supports continual and few-shot continual learning