Huaijiang Sun

Nanjing University of Science and Technology

Papers

Total Citations

H-Index

About

Huaijiang Sun is a leading researcher in computer vision and human motion analysis, with a particular focus on advancing 3D human motion and pose prediction for real-world human-robot interaction. His work addresses a critical limitation in the field: the tendency of existing models to treat motion forecasting as a one-off, short-term process. In his highly cited 2023 paper, **"DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback,"** Sun introduces a novel framework that enables continuous, long-term prediction by incorporating deviation feedback, moving beyond the standard one-second forecasting horizon. This work has garnered **14 citations** and is reshaping how researchers approach dynamic, real-world scenarios. Complementing this, his **"Meta-Auxiliary Learning for Adaptive Human Pose Prediction"** (5 citations) tackles the challenge of generalizability, proposing a meta-learning strategy that adapts pre-trained models to individual test samples on the fly. By pioneering these adaptive and feedback-driven architectures, Sun is laying the groundwork for more intuitive and safe collaboration between humans and intelligent robots, making his contributions essential reading for anyone working at the intersection of deep learning, motion forecasting, and embodied AI.