AI RESEARCH
Uncertainty-Aware (Un)Supervised Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition
arXiv CS.LG
•
ArXi:2606.04798v1 Announce Type: new Sensor-based Human Activity Recognition (HAR) models often degrade on unseen users due to domain shifts caused by individual movement patterns and sensor placement. Practical wearable HAR systems. therefore. require personalization methods that are lightweight, applicable whether calibration data is labeled, unlabeled, or unavailable, and robust under limited calibration.