Zengrong Lin

Papers

Total Citations

H-Index

About

Zengrong Lin is a researcher in computer vision and human-computer interaction, with a primary focus on sign language recognition and multi-modal learning. Their most cited work, "SML: A Skeleton-based multi-feature learning method for sign language recognition" (2024), has garnered 13 citations, establishing a novel framework that integrates skeletal joint data with multiple feature streams to improve the accuracy and robustness of sign language interpretation. This contribution addresses critical challenges in capturing the nuanced, dynamic gestures of sign language, offering a more efficient alternative to traditional video-based methods. By leveraging skeleton-based representations, Lin’s approach reduces computational overhead while enhancing recognition performance, making it particularly valuable for real-time applications and assistive technologies. Their work sits at the intersection of deep learning, gesture analysis, and accessibility research, demonstrating a commitment to bridging communication gaps through technology. Lin’s research not only advances the technical frontier of sign language recognition but also holds significant social impact, promising to empower deaf and hard-of-hearing communities. With growing interest in inclusive AI systems, their contributions are poised to influence future developments in human-centered computing and assistive robotics.