Weiqing Li

Nanjing University of Science and Technology

Papers

Total Citations

H-Index

About

Weiqing Li’s research lies at the dynamic intersection of computer vision and human-robot interaction, with a sharp focus on advancing how machines anticipate and adapt to human motion. Her major contributions center on developing intelligent frameworks that move beyond static, one-off predictions to enable truly responsive robotic systems. In her highly cited work, “DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback” (14 citations), Li reimagines motion forecasting for real-world collaboration, introducing a feedback-driven mechanism that corrects prediction deviations in real time—a critical leap for safe, fluid human-robot teamwork. Her follow-up study, “Meta-Auxiliary Learning for Adaptive Human Pose Prediction” (5 citations), tackles the limitations of generic pre-trained models by proposing a meta-learning approach that adapts predictions to each unique test sample, significantly improving fidelity and generalization. By challenging the conventional “one-off” prediction paradigm, Li’s work directly addresses the unpredictability of human behavior, paving the way for robots that can truly collaborate rather than merely react. Her innovative use of deviation feedback and auxiliary learning marks her as a rising leader in adaptive human motion forecasting, with clear implications for assistive robotics, autonomous driving, and interactive AI systems.