Scholar
Shi, Kaijie
Google Scholar ID: YwlC_qcAAAAJ
memorial university of newfoundland
Citations & Impact
Citations
56
H-index
4
i10-index
2
Publications
8
Co-authors
0
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- - Paper: "Towards Biosignals-Free Autonomous Prosthetic Hand Control via Imitation Learning" (arXiv:2506.08795, 2025)
- - Paper: "Probability-based channel pruning for depthwise separable convolutional networks" (Journal of Computer Science and Technology, 2022)
- - Paper: "Do inpainting yourself: Generative facial inpainting guided by exemplars" (Neurocomputing, 2025)
- - Paper: "GRIG: Data-efficient generative residual image inpainting" (Computational Visual Media, 2024)
- - Paper: "Generative image inpainting with enhanced gated convolution and Transformers" (Displays, 2022)
- - Paper: "TEG: image theme recognition using text-embedding-guided few-shot adaptation" (Journal of Electronic Imaging, 2024)
Research Experience
- - September 2025–April 2026: Participated in the i2I skills training
- - 2025–2026 academic year: Participated in the Translational R&D Program
- - Summer 2024: Attended the Genesis Evolution Program
- - Sept. 2023 - Dec. 2023: TA in Memorial University (Obj-Orient Prgm Human Comp Int)
- - April 2022 - Dec. 2022: Instructor at Wenzhou Business College
- - Dec. 2021 - March 2022: Computer Vision Algorithm Intern at OneFlow Inc
Education
- Ph.D. student since January 2023 in the Ubiquitous Computing and Machine Learning Research Lab (UCML) at the Department of Computer Science at Memorial University of Newfoundland, advised by Prof. Xianta Jiang and Prof. Hanli Zhao.
Background
- Research interests include Geographic Information Science, computer vision, and robot learning. Majored in Geographic Information Science during undergraduate studies, conducted research in computer vision during the master’s program, and then shifted to robot learning for the PhD.
Miscellany
- Open to working remotely for a company in Silicon Valley. Open source code Dynamic-convolution-pytorch, garnering over 550 stars.
Co-authors