AI RESEARCH
BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognition
arXiv CS.CV
•
ArXi:2605.08296v1 Announce Type: new Human Activity Recognition (HAR) from wearable sensors s broad healthcare and behavior science applications. However, data heterogeneity and the scarcity of labeled data limit its real-world generalization. Recent advances in self-supervised learning (SSL) in vision and language domains have shown strong capability for learning generalizable representations from unlabeled data. Yet, few studies have systematically compared the generalization performance of SSL methods or explored how to adapt them for generalizable