Zongyuan Ding
Papers
1
Total Citations
26
H-Index
1
About
Zongyuan Ding is a rising researcher in computer vision and human motion analysis, with a focus on advancing 3D skeleton-based pose forecasting. His work addresses a fundamental challenge in robotics, computer vision, and graphics: predicting future human poses from historical sequences. Ding’s most cited paper, “Hybrid Directed Hypergraph Learning and Forecasting of Skeleton-Based Human Poses” (2024), has already garnered 26 citations, signaling its early impact. In this work, he introduces a novel hybrid directed hypergraph learning framework that improves upon traditional graph convolutional networks (GCNs) by more effectively modeling the complex, hierarchical relationships among human joints. This approach enhances the accuracy and robustness of pose forecasting, with promising applications in human-robot interaction, animation, and autonomous systems. Ding’s contributions are notable for pushing beyond conventional GCN-based methods, offering a more nuanced representation of skeletal dynamics. As his research gains traction, he is establishing himself as an innovator in structured human motion modeling, with potential to influence both theoretical understanding and practical deployment in embodied AI and interactive technologies.
Research Focus
Key Achievements
Top Papers
- 1