Xiaofeng Bie
Papers
1
Total Citations
3
H-Index
1
About
Xiaofeng Bie is a researcher at the forefront of interactive systems and human-robot collaboration, with a primary focus on multimodal human pose estimation (HPE) and personalized adaptation for healthcare and wearable technologies. Their most notable contribution is the development of a meta-transfer-learning-based framework for lower-limb HPE, which addresses the critical challenge of maintaining accurate pose estimation across diverse users without requiring extensive retraining. This work, published in 2025 and already garnering 3 citations, demonstrates a novel approach that combines meta-learning with transfer learning to enable rapid personalization for applications such as controlling cooperative robots and exoskeletons. By tackling the problem of domain shift in human motion data, Bie’s research directly impacts the reliability of healthcare monitoring equipment and assistive devices. Their work stands out for its practical focus on real-world deployment, bridging the gap between laboratory models and adaptive, user-specific systems. Bie’s contributions are particularly relevant for students and researchers interested in the intersection of computer vision, robotics, and personalized healthcare technology.
Research Focus
Key Achievements
Top Papers
- 1