Jiefeng Li
Papers
1
Total Citations
15
H-Index
1
About
Jiefeng Li is a leading researcher in computer vision and machine learning, with a primary focus on human motion analysis, trajectory prediction, and generative modeling. His most influential work introduces a groundbreaking approach to human trajectory prediction through conditionally parameterized normalizing flows, enabling fast, unified, and tractable probabilistic forecasting of future paths. This method addresses critical limitations of prior intractable generative models, achieving state-of-the-art performance for applications in service robotics, autonomous driving, and advanced driver-assistance systems. With over 15 citations since 2021, Li's contributions have rapidly gained recognition for their practical impact on safe and efficient human-robot interaction. His research bridges the gap between theoretical generative modeling and real-world deployment, offering a computationally efficient framework that produces multiple plausible trajectory predictions without sacrificing accuracy. Li's work exemplifies how principled probabilistic methods can solve complex prediction challenges, making him a rising authority in the field of human behavior forecasting.
Research Focus
Key Achievements
Top Papers
- 1