Qingge Ji

China Guangzhou Analysis and Testing Center

Papers

1

Total Citations

3

H-Index

1

About

Qingge Ji is a leading researcher in computer vision and intelligent transportation systems, with a focus on pedestrian behavior modeling and trajectory prediction. Their most cited work introduces the Scene-STGCNN (Scene-Constrained Spatial-Temporal Graph Convolutional Neural Network), a groundbreaking framework that addresses two critical limitations in pedestrian trajectory prediction: the inability to explicitly model how environmental scenes influence individual pedestrian movements, and poor accuracy in crowded scenarios where global social interactions dominate. By integrating a scene-based fine-tuning module with spatial-temporal graph convolutions, Ji’s approach achieves intuitive, interpretable scene–pedestrian relationships while outperforming prior methods in dense crowds. This work has garnered 3 citations since 2023, reflecting its emerging impact. Ji’s research bridges deep learning and geometric graph theory, offering practical advances for autonomous driving, robotics, and surveillance systems. Their contributions stand out for combining theoretical rigor with real-world applicability, making them a rising voice in human-centric AI and spatial intelligence.

Research Focus

Key Achievements

1
H-Index
1
Papers
3
Total Citations
3
Avg Citations/Paper
🏆 Most Cited Paper
Scene-constrained spatial-temporal graph convolutional network for pedestrian trajectory prediction
3 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 1
🏛 Institutions: China Guangzhou Analysis and Testing Center

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago