DML-FitAR: A Deep Metric Learning Approach for IMU-Based Fitness Activity Recognition
Timin Li, Dongmei Li, Yuepeng Chen, Zhuangzhuang Li, Ye Ma, Dongwei Liu, Xuefeng Feng, Ji Yi Wu, Chenyi Guo · 2025
This paper proposes DML-FitAR, a novel deep metric learning framework for IMU-based fitness action recognition, addressing critical challenges in real-world deployment. Unlike traditional transfer learning methods requiring fine-tuning for new action types, DML-FitAR achieves competitive accuracy on unseen actions through a retraining-free paradigm. Evaluated on a custom dataset (560+ fitness actions) and the MyoGYM dataset, DML-FitAR demonstrates superior performance over contrastive learning and visual backbone-based approaches, achieving cross-action-type recognition accuracy ranging from 80% to 90%. Besides that, the framework also exhibits robustness to sensor placement variations and noteworthy cross-dataset generalization.