Kaijie Shi

I have been a 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.

As I enjoy exploring different fields, I majored in Geographic Information Science during my undergraduate studies, conducted research in computer vision during my master’s program, and then shifted to robot learning for my PhD.

I’m open to working remotely for a company in Silicon Valley.

Selected Experience:

-6. Participated in the i2I skills training during September 2025–April 2026.

-5. Participated in the Translational R&D Program during the 2025–2026 academic year.

-4. Attended the Genesis Evolution Program in Summer 2024.

-3. Sept. 2023 - Dec. 2023: TA in Memorial University (Obj-Orient Prgm Human Comp Int).

-2. April 2022 - Dec. 2022: Instructor at Wenzhou Business College.

-1. Dec. 2021 - March 2022: Computer Vision Algorithm Intern at OneFlow Inc.

-0. Open source code Dynamic-convolution-pytorch, garnering over 550 stars.

Selected papers

"Towards Biosignals-Free Autonomous Prosthetic Hand Control via Imitation Learning." arXiv preprint arXiv:2506.08795 (2025). Shi, Kaijie, Wanglong Lu, Hanli Zhao, Vinicius Prado da Fonseca, Ting Zou, and Xianta Jiang. (https://sites.google.com/view/autonomous-prosthetic-hand)

Keywords: Prosthetic hand control, computer vision, imitation learning, generative models

"Probability-based channel pruning for depthwise separable convolutional networks." Journal of Computer Science and Technology 37, no. 3 (2022): 584-600. Zhao, Han-Li, Kai-Jie Shi, Xiao-Gang Jin, Ming-Liang Xu, Hui Huang, Wang-Long Lu, and Ying Liu.

Keywords: Network compression, channel pruning, depthwise separable convolution, batch normalization

"Do inpainting yourself: Generative facial inpainting guided by exemplars." Neurocomputing 617 (2025): 128996. Lu, Wanglong, Hanli Zhao, Xianta Jiang, Xiaogang Jin, Yong-Liang Yang, and Kaijie Shi.

Keywords: Generative adversarial networks, Image generation, Image inpainting, Facial image inpainting

"GRIG: Data-efficient generative residual image inpainting." Computational Visual Media (2024). Lu, Wanglong, Xiaogang Jin, Xianta Jiang, Yongliang Yang, Minglun Gong, Kaijie Shi, Tao Wang, and Hanli Zhao.

Keywords: Image inpainting, few-shot learning, iterative reasoning, residual learning, generative adversarial networks.

"Generative image inpainting with enhanced gated convolution and Transformers." Displays 75 (2022): 102321. Wang, Min, Wanglong Lu, Jiankai Lyu, Kaijie Shi, and Hanli Zhao.

Keywords: Image inpainting, Transformers, Gated convolution, GAN

"TEG: image theme recognition using text-embedding-guided few-shot adaptation." Journal of Electronic Imaging 33, no. 1 (2024): 013028-013028. Wang, Jikai, Wanglong Lu, Yu Wang, Kaijie Shi, Xianta Jiang, and Hanli Zhao.

Keywords: Image theme recognition, image recognition, vision-language pre-training, deep learning