Yuge Gu
Papers
6
Total Citations
174
H-Index
6
About
Yuge Gu is a leading researcher in computer vision for surgical robotics, specializing in the automatic segmentation of surgical instruments from endoscopic images. Their work addresses a critical bottleneck in robotic surgery: enabling machines to accurately identify and track instruments in real-time, despite the challenges of low contrast, complex backgrounds, and occlusions in the surgical field. Gu has pioneered a series of innovative deep-learning architectures that fuse transformer-based attention mechanisms with multi-scale feature extraction. Their most influential work, TMF-Net (52 citations), introduced a transformer-based multiscale fusion network that significantly improved segmentation accuracy. This was followed by DRR-Net (43 citations), which combined dense connections with residual recurrent convolutions, and an attention-guided network (37 citations). Collectively, Gu’s six highly cited papers—including TMA-Net and MAF-Net—have accumulated over 170 citations, establishing a robust foundation for safer, more autonomous surgical robots. Their systematic advancement of segmentation techniques directly supports the next generation of computer-assisted surgery.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6