Scholar
Muyi Sun
Google Scholar ID: Ti7NNqMAAAAJ
School of AI, BUPT (<< NLPR CASIA << BUPT)
Citations & Impact
Citations
686
H-index
16
i10-index
22
Publications
20
Co-authors
12
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Papers published in reputable journals and conferences such as IEEE/ACM TMI, TIFS, TII, TCBB, JBHI, and CVPR. Specific publications include: Pest Manager accepted to Elsevier PR; ReMeREC accepted to ACM MM 2025; DanceEditor accepted to IEEE/CVF ICCV 2025; a paper on Blind Face Restoration Against Adversarial Attacks accepted to IEEE T-IFS; HumanDiffusion accepted to Springer IJCV; two papers on VQAssessment and Efficient VLMs accepted to IEEE/CVF CVPR 2024; a paper on Free-style Text-to-Face Synthesis accepted to IEEE T-PAMI; a paper on Face-Sketch Synthesis accepted to IEEE T-NNLS; a paper on Micro-Motion Human Patterns accepted to ACM MM 2023; a paper on 3D Hand Gesture Prediction accepted to IEEE/CVF CVPR 2023.
Research Experience
- Currently, an Associate Research Fellow at the School of Artificial Intelligence, Beijing University of Posts and Telecommunications, member of the Vision Perception and Generation Laboratory. Previously, a PostDoc Researcher / Assistant Research Fellow at the Center for Research on Intelligent Perception and Computing, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, advised by Prof. Zhenan Sun.
Education
- Ph.D. in Control Science and Engineering from the School of Automation (now AI) at Beijing University of Posts and Telecommunications (BUPT) in 2020, advised by Dr. Hao Dang and Dr. Guanhong Zhang. B.S. in Automation from the School of Automation (now AI) at BUPT in 2015, supervised by Prof. Jun Yang.
Background
- Research interests: Multi-Model Medical Image Analysis, Multi-Model Human-Centric Generation, Efficient and Multi-Modal Medical Image Analysis (Transformer-based, MixUp-based, Knowledge Distillation, MultiModal Learning), Multi-Modal Human Motion Generation (GAN-based, Diffusion-based, MultiModal Learning), and Multi-Model 3D (3D Representation and Generation).
Miscellany
- Personal interests: Dog.Niu and Chou growing up with me and lighting up my life. Some team positions will be jointly trained with the Institute of Automation, Chinese Academy of Sciences or co-supervised with Dr. Xingqun Qi from the Hong Kong University of Science and Technology.
