YU Hong-quan

ZTE (China)

Papers

1

Total Citations

14

H-Index

1

About

YU Hong-quan is a researcher advancing the field of 3D scene understanding through innovative deep learning architectures for point cloud analysis. His primary research focuses on semantic segmentation of 3D point cloud data, a critical task for applications in autonomous navigation, robotics, and environmental reconstruction. His most notable contribution is the KVGCN model, a Graph Convolutional Network that uniquely integrates K-Nearest Neighbor searching with Vector of Locally Aggregated Descriptors (VLAD). This hybrid approach effectively captures both local geometric structures and global contextual features, addressing key challenges in point cloud segmentation. The work has garnered 14 citations, demonstrating its relevance in the rapidly evolving domain of 3D computer vision. By bridging graph neural networks with classical feature aggregation techniques, Hong-quan’s research offers practical solutions for real-world sensing systems, where accurate segmentation is essential for machines to interpret complex environments. His work continues to influence developments in scene understanding and spatial intelligence.

Research Focus

Key Achievements

1
H-Index
1
Papers
14
Total Citations
14
Avg Citations/Paper
🏆 Most Cited Paper
KVGCN: A KNN Searching and VLAD Combined Graph Convolutional Network for Point Cloud Segmentation
14 citations · 2021
📈 Most Prolific Year: 2021 (1 Papers)
🤝 Key Collaborators: 6
🏛 Institutions: ZTE (China)

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago