Serena Yeung
Papers
3
Total Citations
56
H-Index
2
About
Serena Yeung is a leading researcher at the intersection of artificial intelligence, computer vision, and healthcare, with a focus on developing AI systems that perceive and interact with the physical world. Her work spans robotic surgery analysis, 3D human pose estimation, and open-world object detection. Yeung’s most cited paper (47 citations) pioneers the use of AI and computer vision to quantitatively assess technical proficiency in robotic surgery, offering a transformative tool for surgical training and quality assurance. She has also advanced 3D human mesh recovery from single images—a challenge critical for applications in entertainment, robotics, and neuroscience—by introducing domain-adaptive 3D pose augmentation to improve model robustness in real-world settings. More recently, Yeung has tackled open-world object detection, enabling models to recognize novel objects without retraining, a capability essential for reliable deployment in robotics and medical imaging. Her work is notable for bridging foundational AI research with high-impact clinical and real-world applications, demonstrating how computer vision can enhance human performance and safety.
Research Focus
Key Achievements
Top Papers
- 1
- 2Domain Adaptive 3D Pose Augmentation for In-the-Wild Human Mesh Recovery7 citations · 2022
- 3Open World Object Detection in the Era of Foundation Models2 citations · 2023