Xinghui Jing
Papers
1
Total Citations
4
H-Index
1
About
Dr. Xinghui Jing is a rising researcher in computer vision and autonomous systems, whose work centers on pedestrian trajectory prediction—a critical challenge for safe human-robot interaction in autonomous driving and service robotics. Their most-cited paper, "Dual-Alignment Domain Adaptation for Pedestrian Trajectory Prediction" (2024, 4 citations), introduces a novel framework that addresses a key limitation in the field: the performance drop of multi-scene trained models when applied to single-scene tests. By proposing dual-alignment mechanisms, Jing’s work enables models to adapt across different environments without requiring expensive retraining, improving robustness and generalization. This contribution is particularly impactful for real-world deployment, where models must handle diverse, unpredictable pedestrian behaviors. Though early in their career, Jing’s focus on domain adaptation signals a commitment to bridging the gap between lab-trained models and practical, dynamic settings. Their research holds promise for enhancing safety in autonomous navigation and collaborative robotics, marking them as a researcher to watch in the evolving landscape of human-aware AI systems.
Research Focus
Key Achievements
Top Papers
- 1Dual-Alignment Domain Adaptation for Pedestrian Trajectory Prediction4 citations · 2024