BasketHAR: A Multimodal Dataset for Human Activity Recognition and Sport Analysis in Basketball Training Scenarios

2026-04-18

AI Summary

Existing human activity recognition (HAR) datasets are predominantly limited to basic daily activities and lack high-quality, multimodal data tailored to specialized sports contexts. This work addresses this gap by constructing and releasing the first multimodal HAR dataset specifically designed for basketball training, integrating inertial measurement unit data (accelerometer, gyroscope, magnetometer), physiological signals (heart rate, skin temperature), and synchronized video recordings across a range of professional-level basketball maneuvers. The dataset exhibits high complexity and practical relevance, supporting advanced HAR research while also establishing a reliable benchmark for athletic performance analysis and automated generation of specialized training reports. To facilitate fair and consistent evaluation, the release includes standardized baseline alignment protocols.

Technology Category

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

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Human Activity Recognition (HAR) involves the automatic identification of user activities and has gained significant research interest due to its broad applicability. Most HAR systems rely on supervised learning, which necessitates large, diverse, and well-annotated datasets. However, existing datasets predominantly focus on basic activities such as walking, standing, and stair navigation, limiting their utility in specialized contexts like sports performance analysis. To address this gap, we present BasketHAR, a novel multimodal HAR dataset tailored for basketball training, encompassing a diverse set of professional-level actions. BasketHAR includes comprehensive motion data from inertial measurement units (accelerometers and gyroscopes), angular velocity, magnetic field, heart rate, skin temperature, and synchronized video recordings. We also provide a baseline multimodal alignment method to benchmark performance. Experimental results underscore the dataset's complexity and suitability for advanced HAR tasks. Furthermore, we highlight its potential applications in the analysis of basketball training sessions and in the generation of specialized performance reports, representing a valuable resource for future research in HAR and sports analytics. The dataset are publicly accessible at https://huggingface.co/datasets/Xian-Gao/BasketHAR licensed under Apache License 2.0.

Problem

• Human Activity Recognition
• sports performance analysis
• multimodal dataset
• basketball training
• specialized contexts

Innovation

• multimodal dataset
• human activity recognition
• basketball training
• inertial measurement units
• sports analytics