Yinhong Qin

Papers

Total Citations

H-Index

About

Yinhong Qin is a rising researcher in computer vision and medical AI, with a focus on surgical gesture recognition and zero-shot learning. Her most-cited work, “Zero-shot prompt-based video encoder for surgical gesture recognition” (2024, 5 citations), introduces a novel approach that leverages prompt-based video encoding to enable surgical AI systems to recognize gestures across diverse procedures without requiring extensive annotated datasets. This contribution addresses a critical bottleneck in surgical robotics and computer-assisted intervention: the need for models that generalize to new, unseen surgical tasks. By advancing zero-shot capability in video understanding, Qin’s research promises to reduce the data burden for training robust surgical AI, potentially accelerating the adoption of intelligent systems in operating rooms. Her work sits at the intersection of deep learning, video analysis, and medical application, demonstrating how prompt engineering can unlock new efficiencies in healthcare AI. Though early in her career, Qin’s innovative approach to bridging domain gaps in surgical gesture recognition marks her as a promising contributor to the field, with implications for safer, more adaptable robotic surgery.