Yongjing Ye

Papers

Total Citations

132

H-Index

About

Yongjing Ye is a rising researcher in computer vision, with a focused expertise in human motion prediction and graph-based deep learning. Their most significant contribution is the development of the Spatio-Temporal Gating-Adjacency Graph Convolutional Network (GCN), a novel architecture that addresses the fundamental challenge of forecasting future human motion from historical sequences. This work, published in 2022, has rapidly gained recognition, accumulating over 122 citations, underscoring its impact on the field. Ye’s research is particularly vital for high-stakes applications such as autonomous driving and robotics, where accurate anticipation of human movement is critical for safety and interaction. By innovatively modeling the dynamic relationships between different body joints through a gating mechanism, Ye’s approach improves the fidelity and long-term stability of motion predictions. This achievement not only advances the theoretical understanding of spatio-temporal graph modeling but also provides a practical tool for real-world systems. For students and researchers, Ye’s work exemplifies how targeted architectural innovations in GCNs can solve complex, real-world problems, marking them as a promising voice in the future of human-centered AI.