伍文瀚-云南马来亚学院

伍文瀚

发布时间：2026年04月24日 点击：

姓名 / Name: 伍文瀚 / Wenhan Wu

职务 / Position: 博士，讲师 / Ph.D., Lecturer

邮箱 / Email: wenhanwu95@ynu.edu.cn

地址 / Address: 云南马来亚学院（现代工学院） / Yunnan-Malaya Institute (School of Engineering), Yunnan University, Kunming, China

个人简介 / Resume

伍文瀚，云南大学云南马来亚学院讲师。博士毕业于北卡罗来纳大学夏洛特分校（UNC Charlotte）计算与信息学院，师从 Aidong Lu 教授，联合导师为 Chen Chen 教授。加入北卡罗来纳大学夏洛特分校之前，于 2020 年在史蒂文斯理工学院（SIT）获得电气与计算机工程硕士学位，于 2018 年在电子科技大学（UESTC）信息与通信工程学院获得电子信息工程学士学位（英才学院）。主要从事深度学习、计算机视觉、以人为中心的视频理解（动作识别、运动分析与姿态估计）等方向研究。担任 WACV、ICME、NeurIPS、ACM Multimedia、ICML 等国际会议审稿人，以及 ACM Computing Surveys、IEEE Transactions on Image Processing、IEEE Transactions on Multimedia、IEEE Transactions on Circuits and Systems for Video Technology、Pattern Recognition 等期刊审稿人。截至 2026年4月，谷歌学术引用1300余次。

Wenhan Wu is a Lecturer at the Yunnan-Malaysia College, Yunnan University. He received his Ph.D. from the College of Computing and Informatics at the University of North Carolina at Charlotte, under the supervision of Prof. Aidong Lu, with Prof. Chen Chen as his co-advisor. Prior to joining UNC Charlotte, he earned his M.S. degree in Electrical and Computer Engineering from the Stevens Institute of Technology in 2020, and his B.Eng. degree in Electronic Information Engineering from the University of Electronic Science and Technology of China (UESTC) in 2018. His research interests include deep learning, computer vision, human-centered video understanding, action recognition, motion analysis, and pose estimation. He also serves as a reviewer for leading international conferences, including WACV, ICME, NeurIPS, ACM Multimedia, and ICML, as well as journals such as ACM Computing Surveys, IEEE Transactions on Image Processing, IEEE Transactions on Multimedia, IEEE Transactions on Circuits and Systems for Video Technology, and Pattern Recognition. As of April 2026, his Google Scholar citations exceed 1,300.

Google Scholar: https://scholar.google.com/citations?user=AybK46kAAAAJ&hl=en&authuser=1

教育和工作经历 / Education & Work Experience

2026.3–至今云南马来亚学院（现代工学院），讲师

2021.08 – 2025.12 北卡罗来纳大学夏洛特分校，计算机科学专业, 理学博士

2020.09 – 2021.07 北卡罗来纳大学夏洛特分校，电气与计算机工程，理学博士

2018.09 – 2020.05 史蒂文斯理工学院，电气与计算机工程，理学硕士

2014.09–2018.06 电子科技大学，电子信息工程专业，学士

额外教学与研究经历：

1. 北卡罗来纳大学夏洛特分校计算机科学系 2024 – 2025 教学助理（ITCS-3156-机器学习导论，2024 年秋季 / 2025 年春季 / 2025 年秋季）

2. 北卡罗来纳大学夏洛特分校计算机科学系 2021 – 2024 研究助理（研究方向：Skeleton-based Action Recognition）

3. 北卡罗来纳大学夏洛特分校电气与计算机工程系 2020 – 2021 教学助理（ECGR3155-系统与电子实验室，ECGR-2181-001-逻辑系统设计 I，ECGR3090/4090-机器学习导论）

科研项目 / Research Projects

1. 美国国家科学基金（NSF1840080），FW-HTF: Future of Firefighting and Career Training - Advancing Cognitive, Communication, and Decision Making Capabilities of Firefighters，149 万（美元），2021-9-1 至 2024-9-30，参与

代表性论文 / Representative Publications

1. Guangyu Sun, Wenhan Wu, Zhishuai Guo, Ziteng Wang, Pegah Khosravi, Chen Chen. Unlocking Multi-Site Clinical Data: A Federated Learning Approach to Privacy-First Child Autism Behavior Analysis. CVPR 2026 Workshop on Computer Vision for Children – Proceedings Track, 2026（CVPR Workshop，CCF A 类会议 Workshop，计算机视觉顶级会议，儿童计算机视觉方向）

2. Wenhan Wu, Zhishuai Guo, Chen Chen, Aidong Lu. UniSTFormer: Unified Spatio-Temporal Lightweight Transformer for Efficient Skeleton-Based Action Recognition. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2026（ICASSP，口头报告，CCF B 类会议，信号处理顶级会议）

3. Umesh Vangapally, Wenhan Wu, Chen Chen, Zhishuai Guo. Communication-Efficient Federated AUC Maximization with Cyclic Client Participation. Transactions on Machine Learning Research, 2026（TMLR，机器学习期刊）

4. Wenhan Wu, Zhishuai Guo, Chen Chen, Hongfei Xue, Aidong Lu. Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-Based Action Recognition. IEEE/CVF International Conference on Computer Vision, 2025（ICCV，CCF A 类会议，计算机视觉顶级会议）

5. Wenhan Wu, Pengfei Wang, Chen Chen, Aidong Lu. FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition. The 19th IEEE International Conference on Automatic Face and Gesture Recognition, 2025（FG 2025，口头报告，CCF C 类会议）

6. Wenhan Wu, Ce Zheng, Zihao Yang, Chen Chen, Srijan Das, Aidong Lu. Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer. ACM Multimedia, 2024（ACM MM，CCF A 类会议，多媒体顶级会议）

7. Ce Zheng*, Wenhan Wu*, Taojiannan Yang, Sijie Zhu, Chen Chen, Ruixu Liu, Ju Shen, Nasser Kehtarnavaz, Mubarak Shah. Deep Learning-Based Human Pose Estimation: A Survey. ACM Computing Surveys, 2023（共同一作，IF 影响因子：23.8，JCR Q1 区，中科院 1 区顶级期刊，计算机科学理论与方法类排名第 1）

8. Wenhan Wu, Yilei Hua, Ce Zheng, Shiqian Wu, Chen Chen, Aidong Lu. SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition. Workshop on Human Motion Analysis (HMA) in International Conference on Multimedia and Expo, 2023（ICME Workshop，CCF B 类会议 Workshop）

9. Yilei Hua, Wenhan Wu, Ce Zheng, Aidong Lu, Mengyuan Liu, Chen Chen, Shiqian Wu. Part Aware Contrastive Learning for Self-Supervised Action Recognition. The International Joint Conference on Artificial Intelligence, 2023（IJCAI，CCF B 类会议，人工智能顶级会议，录用率 15%）

上一篇：汤智文

下一篇：汤智文

人工智能

人工智能

伍文瀚

友情链接