CV

Contact

• Name: Hu Xue
• Affiliation: School of Computer Science and Technology, Chongqing University of Post and Telecommunications, Chongqing, China
• Email: huxue178@gmail.com
• GitHub: hu-xue
• ORCID: 0009-0001-7232-7403

Research Profile

I am a doctoral student working on multimodal perception, deep learning, sensor fusion, and robust positioning. My research focuses on designing effective feature-fusion methods for challenging real-world environments, including visible-thermal infrared object tracking and vision-aided GNSS positioning in urban canyons.

Education

• Ph.D. Student, Computer Science and Technology
  • Chongqing University of Post and Telecommunications, Chongqing, China
  • Research areas: multimodal learning, visual tracking, sensor fusion, and positioning

Research Interests

• Multimodal learning and feature fusion
• Visible-thermal infrared object tracking
• Vision-aided GNSS positioning
• Parameter-efficient deep learning
• Robust perception in complex environments

Publications

Feature Fusion and Enhancement for Lightweight Visible-Thermal Infrared Tracking via Multiple Adapters

H. Xue, H. Zhu, Z. Ran, X. Tang, G. Qi, Z. Zhu, S.-C. Kuok, and H. Leung. (2026). "Feature Fusion and Enhancement for Lightweight Visible-Thermal Infrared Tracking via Multiple Adapters." IEEE Transactions on Circuits and Systems for Video Technology, 36(1), 959-970. doi:10.1109/TCSVT.2025.3595632.

VGPNet: A Vision-aided GNSS Positioning Framework with Cross-Channel Feature Fusion for Urban Canyons

H. Xue, H. Zhu, L. Wang, S.-C. Kuok, B. Li, H. Zhang, G. Li, and H. Leung. (2025). "VGPNet: A Vision-aided GNSS Positioning Framework with Cross-Channel Feature Fusion for Urban Canyons." IEEE Transactions on Instrumentation and Measurement, 74, 1-13. doi:10.1109/TIM.2025.3635311.

Selected Research Projects

• MFJA: Lightweight Visible-Thermal Infrared Tracking
  • Developed a multiple-adapter framework for RGB-T tracking with feature fusion and joint enhancement.
  • Improved tracking robustness while introducing only a small number of trainable parameters.
  • Code: github.com/hu-xue/MFJA
• VGPNet: Vision-aided GNSS Positioning
  • Designed a framework that fuses sky-pointing fisheye imagery and GNSS observations for urban-canyon positioning.
  • Proposed cross-channel feature fusion for adaptive satellite weighting and bias correction.
  • Code: github.com/hu-xue/VGPNet

Skills

• Programming: Python, MATLAB, C/C++
• Deep Learning: PyTorch, transformer-based models, parameter-efficient fine-tuning
• Research Methods: multimodal feature fusion, object tracking, GNSS data processing, experimental evaluation
• Tools: Git, Linux, LaTeX

Academic Service

• Manuscript preparation, literature review, experimental design, and reproducible code release for peer-reviewed journal publications.