石武祯，博士，深圳大学电子与信息工程学院助理教授,特聘副研究员，硕士研究生导师，入选鹏城孔雀C档特聘岗，IEEE高级会员。于2020年4月获哈尔滨工业大学工学博士学位，于2020年6月加入丁文华院士领导的广东省数字创意技术工程实验室。他获得哈尔滨工业大学第23届优秀博士学位论文奖和2021年黑龙江省人工智能学会优秀博士学位论文奖。他的研究方向包括图像/视频压缩与增强、情感计算、AIGC等，已发表学术论文40余篇，其中代表性工作成果发表在IEEE TIP、IEEE TCSVT、IEEE TMM、IEEE TII和IEEE TIM等顶级国际期刊以及CVPR和DCC等顶级国际会议上，入选ESI高被引论文1篇。他作为主持人申请获批国家级、省级、市级科研项目以及深圳大学高端人才科研启动项目各1项，作为核心参与人申请获批国家自然科学基金联合基金项目1项、广东省重点领域研发项目1项、深圳市自然科学基金面上项目1项以及小米公司合作研发项目1项。

办公室：深圳大学沧海校区致真楼L6-906

Email: wzhshi@szu.edu.cn

研究兴趣：

图像/视频压缩与增强、情感计算、AIGC

科研项目：

[1] 面向人类和机器视觉的图像和视频低时延深度压缩方法，国家自然科学基金青年基金，2022.01-2024.12，主持。

[2] 融合编码压缩先验的视频增强方法，广东省自然科学基金面上项目，2021.01-2023.12，主持。

[3] 基于深度学习的图像和视频压缩感知，深圳市高等院校稳定支持计划面上项目，2021.01-2022.12，主持。

[4] 低复杂度的高质量4K/8K 超高清视频生成关键技术研究，深圳大学新引进高端人才科研启动项目，2023.01-2025.12，主持。

[5] 5G 超低延时超高清视频编解码芯片研发及应用，广东省重点领域研发项目，2022.01-2024.12，参与。

[6] 面向高动态范围显示的视觉显著性预测研究，深圳市自然科学基金面上项目，2022.10-2025.10，参与。

[7] 可跨域少样本学习的隐写分析网络研究, 国家自然科学基金委员会联合基金项目,2023.01-2026.12, 参与。

部分代表性论文：

[1]W. Shi, J. Su, Y. Wen, Y. Liu. "Light field image super-resolution using a Content-Aware Spatial-Angular Interaction network." Displays (2024): 102782.

[2]W. Shi, F. Tao, Y. Wen. "Joint super-resolution-based fast face image coding for human and machine vision." The Visual Computer (2024): 1-14.

[3]B. Yao, W. Shi*. "Speaker-Centric Multimodal Fusion Networks for Emotion Recognition in Conversations." ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2024.

[4]S. Meng, W. Shi*. "Fusing Structure and Appearance Features in Facial Expression Recognition Transformer." ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2024.

[5]Y. Wen, Y. Wu, L. Bi, W. Shi*, et al. "A Transformer-Assisted Cascade Learning Network for Choroidal Vessel Segmentation." Journal of Computer Science and Technology 39.2 (2024): 286-304.

[6]Z. Yin, Z. Wu, W. Shi. "Scalable compressive sampling network with progressive hierarchical subspace learning." Pattern Recognition 156 (2024): 110769.

[7]W. Shi, D. Li, Y. Wen and W. Yang, "Occlusion-Aware Graph Neural Networks for Skeleton Action Recognition," in IEEE Transactions on Industrial Informatics, vol. 19, no. 10, pp. 10288-10298, Oct. 2023.

[8]W. Shi, F. Tao and Y. Wen, "Structure-Aware Deep Networks and Pixel-Level Generative Adversarial Training for Single Image Super-Resolution," in IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-14, 2023, Art no. 5007614.

[9]W. Shi, Z. Liu, Y. Li, Y. Wen. "Light-weight 3D mesh generation networks based on multi-stage and progressive knowledge distillation." Displays 80 (2023): 102527.

[10]W. Shi, and S. Liu. "Hiding message using a cycle generative adversarial network." ACM Transactions on Multimedia Computing, Communications and Applications 18.3s (2022): 1-15.

[11]Z. Yin, W. Shi, Z. Wu, J. Zhang, “Multilevel wavelet-based hierarchical networks for image compressed sensing”, Pattern Recognition, 2022, 129: 108758.

[12]W. Yang and W. Shi, "Detail Generation and Fusion Networks for Image Inpainting," ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, Singapore, 2022, pp. 2335-2339.

[13]D. Li, Dan, and W. Shi*. "Partially occluded skeleton action recognition based on multi-stream fusion graph convolutional networks." Advances in Computer Graphics: 38th Computer Graphics International Conference, CGI 2021, Virtual Event, September 6–10, 2021, Proceedings 38. Springer International Publishing, 2021.

[14]W. Shi, S. Liu, F. Jiang and D. Zhao, "Video Compressed Sensing Using a Convolutional Neural Network," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 2, pp. 425-438, Feb. 2021.

[15]W. Shi, F. Jiang, S. Liu and D. Zhao, "Image Compressed Sensing Using Convolutional Neural Network," in IEEE Transactions on Image Processing, vol. 29, pp. 375-388, 2020.

[16]W. Shi, F. Jiang, S. Liu, D. 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.

[17]W. Shi, F. Jiang, S. Zhang, R. Wang, D. Zhao, H. Zhou. "Hierarchical residual learning for image denoising." Signal Processing: Image Communication 76 (2019): 243-251.

[18]W. Shi, F. Jiang, S. Liu and D. Zhao, "Multi-Scale Deep Networks for Image Compressed Sensing," 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece, 2018, pp. 46-50.

[19]W. Shi, F. Jiang and D. Zhao, "Single image super-resolution with dilated convolution based multi-scale information learning inception module," 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China, 2017, pp. 977-981.

[20]W. Shi, F. Jiang, S. Zhang and D. Zhao, "Deep networks for compressed image sensing," 2017 IEEE International Conference on Multimedia and Expo (ICME), Hong Kong, China, 2017, pp. 877-882.

最新发表论文详见个人Google学术网页：

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