王书润
一、个人简介
王书润，香港城市大学博士，硕士生导师。聚焦具身智能，机器视觉表示、图像视频编码等领域的研究与标准化，是国际视频标准领域的青年骨干专家。担任国际视频编码标准组织 JVET AHG8 联合主席、MPEG机器视觉编码（VCM）的探索实验与核心实验协调人。发表学术论文 15 篇，申请专利 18 项，授权4项，提交国际标准提案 32 项，其中 9 项被 JVET 采纳，为我国在国际视频编码标准领域提升话语权提供了技术支撑。是IEEE ICME workshop 2024、2025 TPC 成员，PCS2024 Special Session组织者，担任IEEE TVSVT，TMM，ICASSP，ACMMM等期刊和会议审稿人。
二、研究领域
具身智能、机器视觉表示、图像视频编码。欢迎计算机、电子、数学等相关专业的本科生、研究生加入本团队。
三、教育背景
2012.09–2016.07 北京大学 数学与应用数学 学士
2016.09–2019.06 北京大学 计算机科学与技术 硕士
2019.09–2023.06 香港城市大学 计算机科学与技术 博士
四、工作经历
2023.07–2026.02 阿里巴巴集团达摩院 高级算法工程师
2026.03-至今，中山大学，集成电路学院，预聘助理教授（副教授职务）
五、部分代表性成果
（1）代表性论文
1. S. Wang, Z. Wang, S. Wang, Y. Ye, “Deep image compression towards machine vision: A unified optimization framework”, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022.
2. S. Wang, S. Wang, W. Yang, et al., “Towards analysis-friendly face representation with scalable feature and texture compression”, IEEE Transactions on Multimedia (TMM), 2021.
3. S. Wang, S. Wang, W. Yang, et al., “Teacher-student learning with multi-granularity constraint towards compact facial feature representation”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021.
4. S. Wang, Z. Wang, S. Wang, Y. Ye, “End-to-end compression towards machine vision: Network architecture design and optimization”, IEEE Open Journal of Circuits and Systems (OJCAS), 2021.
5. S. Wang, S. Wang, Y. Ye, “Overview of visual signal compression towards machine vision”,Proceedings of the 3rd Mile-High Video Conference (ACMMHV), 2024.
6. B. Li, S. Wang, S. Wang, Y. Ye, “High Efficiency Image Compression for Large VisualLanguage Models”, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024.
7. Z. Wang, B. Chen, S. Wang, S. Wang, Y. Ye, S. Ma, “Ultra-Low Bitrate Face Video Compression Based on Conversions from 3D Keypoints to 2D Motion Map”, IEEE Transactions on Image Processing (TIP), 2024.
（2）授权专利
1. S. Wang, Z. Wang, Y. Ye, S. Wang, METHODS AND SYSTEMS FOR TEMPORAL RESAMPLING FOR MULTI-TASK MACHINE VISION, US 12003728B2.
2. S. Wang, Z. Wang, Y. Ye, S. Wang, METHODS AND NON-TRANSITORY COMPUTER READABLE STORAGE MEDIUM FOR PRE-ANALYSIS BASED RESAMPLING COMPRESSION FOR MACHINE VISION, US 12375678B2.
3. S. Wang, Z. Wang, Y. Ye, S. Wang, PRE-ANALYSIS BASED IMAGE COMPRESSION METHODS, US 12439094В2.
（3）部分已采纳的国际标准提案
1. B. Li, S. Wang, J. Chen, Y. Ye, S. Wang, “AHG15: Feature based Encoder-only algorithms for the Video Coding for Machines”, JVET-AC0086, Jan. 2023.
2. S. Wang, B. Li, J. Chen, Y. Ye, “AHG8: Pre-analysis based adaptive spatial resampling algorithm for machine vision”, JVET-AI0254, Jul. 2024.
3. S. Wang, J. Chen, Y. Ye, B. Li, S. Wang, “AHG8: Pre-analysis based adaptive temporal resampling algorithm for machine vision”, JVET-AJ0254, Nov. 2024.
4. S. Wang, J. Chen, Y. Ye, Binzhe Li, “AHG8: On combination of adaptive temporal resampling and post-processing algorithms for machine vision”, JVET-AK0094, Jan. 2025.