Yisu Wang
Papers
1
Total Citations
21
H-Index
1
About
Yisu Wang is a researcher whose work lies at the intersection of deep learning and spatiotemporal data analysis, with a particular focus on trajectory prediction. Their most-cited paper, "An efficient Spatial–Temporal model based on gated linear units for trajectory prediction" (2021, 21 citations), introduces a novel architecture that leverages gated linear units to efficiently capture both spatial dependencies and temporal dynamics in movement data. This contribution addresses a critical challenge in autonomous systems and urban computing: accurately forecasting future paths of moving objects while maintaining computational efficiency. Wang's model stands out for its ability to balance predictive accuracy with reduced model complexity, making it suitable for real-time applications. The work has garnered attention for its practical implications in areas such as autonomous driving, pedestrian tracking, and robotics. By advancing the efficiency of spatiotemporal modeling, Yisu Wang has provided a valuable tool for researchers and engineers working on motion prediction, demonstrating how careful architectural design can yield both performance gains and operational feasibility.
Research Focus
Key Achievements
Top Papers
- 1