LLM-Guided Exemplar Selection for Few-Shot Wearable-Sensor Human Activity Recognition
基于大语言模型的示例选择用于少样本可穿戴传感器人体活动识别
机构 * Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Kitakyushu, Japan(九州工学院生命科学与系统工程研究生院,日本)
专题命中 测试时计算 :reasoning(abstract);分类 cs.CL、cs.AI
AI总结 本文提出基于大语言模型的示例选择方法,通过语义先验和结构几何线索提升少样本可穿戴传感器人体活动识别的性能。
Comments This paper has been accepted for presentation at ABC 2026. The manuscript is under revision prior to camera-ready submission
Journal ref International Journal of Activity and Behavior Computing 2026, Vol. 2026, No. 1, 1-34