Zhenfeng Zhu
Papers
1
Total Citations
10
H-Index
1
About
Zhenfeng Zhu is a researcher at the forefront of computer vision and medical AI, with a particular focus on surgical scene understanding and automated report generation. His most influential work introduces the Scene Graph-Guided Transformer (SGT), a novel framework that leverages structured scene graphs to guide the generation of coherent surgical reports from video data. This approach addresses the critical challenge of translating complex visual information in the operating room into accurate, narrative documentation, directly impacting surgical training and workflow efficiency. With his top-cited paper accumulating 10 citations, Zhu’s contributions are gaining traction in the emerging field of surgical AI, where his work stands out for its innovative integration of graph-based reasoning with transformer architectures. By enabling machines to not only see but also semantically interpret surgical procedures, Zhu is helping to bridge the gap between raw visual data and clinically meaningful outputs, paving the way for smarter, more autonomous surgical assistance systems.
Research Focus
Key Achievements
Top Papers
- 1SGT: Scene Graph-Guided Transformer for Surgical Report Generation10 citations · 2022