1. Basic Information

lTitle:  Associate Professor

lEmail:  wzhshi@.szu.edu.cn

lOffice:  Room 906, Zhizhen Building

lGoogle Scholar Website: https://scholar.google.com/citations?hl=zh-CN&user=LpyVymMAAAAJ

2. Brief Introduction

Dr. Wuzhen Shi (tenured Associate Professor, Doctoral and Master’s Supervisor; IEEE Senior Member, CCF Senior Member) received his Ph.D. degree in Computer Applied Technology from Harbin Institute of Technology in April 2020, and joined the College of Electronics and Information Engineering at Shenzhen University in June 2020. He was awarded the 23rd Outstanding Doctoral Dissertation Award of Harbin Institute of Technology and the 2021 Outstanding Doctoral Dissertation Award from the Heilongjiang Artificial Intelligence Society. His research interests include image and video compression and enhancement, affective computing, and generative AI (AIGC). He has published over 60 papers, with representative works appearing in top international journals such as IEEE TIP, IEEE TCSVT, IEEE TMM, IEEE TII and IEEE TIM, as well as leading conferences including CVPR, AAAI, and DCC. One of his papers has been recognized as an ESI Highly Cited Paper. His research has been supported by the National Key R&D Program of China, the National Natural Science Foundation of China, the Natural Science Foundation of Guangdong Province, and the Shenzhen Science and Technology Innovation Commission. He has served as a reviewer for more than 20 international journals and conferences, including IEEE TPAMI, IEEE TIP, IEEE TCSVT, IEEE TII, and IEEE JSTSP.

3. Current Research Directions

[1]Image/Video Compression and Enhancement

[2]Affective Computing

[3]AIGC

4. Representative Publications

[1]Wuzhen Shi, Shuai Wang, Zibang Xue, Yang Wen. Diff-KATKG: Diffusion-based Talking Head Generation with Joint Keypoint and Action unit Guidance[J]. Pattern Recognition 178 (2026) 113368.

[2]Wuzhen Shi, Wu Yang, Zhihao Wu, Yang Wen. Validity-Aware Context Modeling for Gradient-Guided Image Inpainting [J]. Information Fusion 131 (2026) 104162.

[3]Wuzhen Shi, Youwei Pan, et al. Multi-scale Transformer for Image Restoration [J]. CAAI Transactions on Intelligence Technology, 2026, 11: 41–54.

[4]Wuzhen Shi, Aixue Yin, Yingxiang Li, Yang Wen. Edge-guided 3D reconstruction from multi-view sketches and RGB images[J]. Pattern Recognition, 2025, 163: 111462.

[5]Wuzhen Shi, Zibang Xue, Yang Wen. Keypoints and Action Units Jointly Drive Talking Head Generation for Video Conferencing[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2025, 35(9): 8692-8706.

[6]Wuzhen Shi, Xuping Chen, Biyun Yao, Yang Wen,Bin Sheng. Identity and Modality Attributes Driven Multimodal Fusion Networks for Emotion Recognition in Conversations[J]. EEE Transactions on Multimedia, 2025, 27: 4361-4371

[7]Wuzhen Shi, Dan Li, Yang Wen, Wu Yang. Occlusion-aware graph neural networks for skeleton action recognition[J]. IEEE Transactions on Industrial Informatics, 2023,19(10): 10288-10298.

[8]Wuzhen Shi, Shaohui Liu, Feng Jiang, Debin Zhao. Video compressed sensing using a convolutional neural network [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31 (2), 425-438.

[9]Wuzhen Shi, Feng Jiang, Shaohui Liu, Debin Zhao. Image compressed sensing using convolutional neural network [J]. IEEE Transactions on Image Processing, 2020, 29: 375-388.

[10]Wuzhen Shi, Feng Jiang, Shaohui Liu, Debin Zhao. Scalable convolutional neural network for image compressed sensing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 12290-12299.