Ka Chun Cheung

Hong Kong Baptist University, Nvidia (United Kingdom)

Papers

4

Total Citations

106

H-Index

3

About

Ka Chun Cheung is a leading researcher in 3D computer vision and machine learning, with a focus on advancing autonomous driving and robotics. His most impactful work, **MPPNet** (79 citations), introduces a flexible framework for 3D temporal object detection that uses proxy points to intertwine multi-frame features, significantly improving accuracy and reliability in point cloud sequences. This innovation addresses a critical need for robust perception in dynamic environments. Cheung also contributed to **TrajectoryFormer** (12 citations), a transformer-based model for 3D multi-object tracking that leverages predictive trajectory hypotheses to enhance tracking-by-detection paradigms. Beyond 3D vision, his work on machine learning for partial differential equations (12 citations) bridges computational science and AI, showcasing his versatility. With over 100 total citations, Cheung’s research is shaping the future of autonomous systems, offering practical solutions for real-world applications like self-driving vehicles and service robots. His ability to integrate temporal reasoning with deep learning marks him as a key figure in advancing 3D perception technologies.

Research Focus

Key Achievements

3
H-Index
4
Papers
106
Total Citations
27
Avg Citations/Paper
🏆 Most Cited Paper
MPPNet: Multi-frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
79 citations · 2022
📈 Most Prolific Year: 2022 (2 Papers)
🤝 Key Collaborators: 10
🏛 Institutions: Hong Kong Baptist University, Nvidia (United Kingdom)

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago