ViPoser: Sparse-IMU Based Human Pose Estimation with Distilled Vision Foundation Priors
Hanyu Zeng, et al. (2026). "ViPoser: Sparse-IMU Based Human Pose Estimation with Distilled Vision Foundation Priors." ACM MobiCom 2026.
CV
Education
- Ph.D in Information Science, University of Pittsburgh, 2028 (expected)
- M.S. in Intelligent Systems, National University of Singapore, 2023
- B.S. in Communication Engineering, University of Electronic Science and Technology of China, 2021
- B.S. in Electronic Engineering, University of Glasgow, 2021
Work experience
- Spring 2022: Research Assistant
- Illinois Advanced Research Center at Singapore
- Duties included: Working on anomaly detection in smart grid systems.
- Supervisor: Lou, Xin and Zhou, Pengfei
- 2023.07-2023.12: Machine Learning Algorithm Engineer
- MeiTuan
- Duties included: Individually developing a multimodal AI assistant that can do hotel recommendation and questions answering by text and image using JAVA and Python.
- Supervisor: Mao, Yu
- 2024.01-Present: Teaching Assistant
- University of Pittsburgh
- Duties included: Algorithm Design, Intro to Neural Networks, and Application of Networks.
- Supervisor: Zhou, Pengfei
- 2025.02-Present: Research Scientist Intern
- Mitsubishi Electric Research Laboratories (MERL)
- Duties included: My research focusing on anomaly detection in IoT system and cybersecurity.
- Supervisor: Wang, Ye
Skills
- Proficient languages: C, Python, R, Java, SQL
- Deep learning frameworks: PyTorch, TensorFlow
- Tools: LaTex, GIT
Publications
Talks
Detecting Cyber Attacks in Smart Grids with Massive Unlabeled Sensing Data
Conference proceedings talk at 2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Singapore