Xiaoning Sun

Nanjing University of Science and Technology

Papers

Total Citations

H-Index

About

Xiaoning Sun is a leading researcher in computer vision and human motion analysis, with a focus on advancing human-robot interaction and embodied AI. Her key research areas include 3D human motion prediction, temporal sequence modeling, and feedback-driven learning systems. Sun’s most notable contribution, DeFeeNet (2023), introduces a groundbreaking framework for consecutive 3D human motion prediction that incorporates deviation feedback—a paradigm shift from traditional one-off, short-term forecasting. By enabling models to iteratively correct predictions over extended time horizons, her work addresses critical limitations in real-world applications like collaborative robotics and autonomous systems. With 14 citations in its first year, DeFeeNet has already influenced subsequent research in long-term motion forecasting. Sun’s approach rethinks the fundamental task design, moving beyond the conventional 1-second prediction window to support continuous, adaptive motion understanding. Her research bridges the gap between theoretical modeling and practical deployment, making her a rising voice in the field. For students and researchers, Sun’s work exemplifies how challenging core assumptions can unlock new capabilities in human-aware AI systems.