Papers
2
Total Citations
13
H-Index
2
About
Hui Li Tan is a researcher at the forefront of 3D computer vision and human-robot interaction, with a focus on enabling intelligent systems to understand and collaborate in complex environments. Her key research areas include few-shot learning on point clouds and task-oriented multi-modal question answering. Tan’s major contribution is the development of Cascade Graph Neural Networks for Few-Shot Learning on Point Clouds, a pioneering approach that addresses the critical challenge of learning from limited annotated 3D data—a bottleneck for applications in autonomous driving, robotics, and remote sensing. This work, which has garnered 9 citations, demonstrates her ability to push the boundaries of deep learning in sparse data regimes. Additionally, her 2020 paper on Task-Oriented Multi-Modal Question Answering for Collaborative Applications introduces a novel QA task and dataset designed to enhance human-robot collaboration, enabling cobots to understand and respond to complex, task-oriented inquiries. With 4 citations, this work underscores her commitment to bridging the gap between AI and practical, real-world collaboration. Tan’s research not only advances theoretical understanding but also has tangible implications for safer, more intuitive autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1Cascade Graph Neural Networks for Few-Shot Learning on Point Clouds9 citations · 2023
- 2