武寒波 - 个人主页

助理教授

浪潮人工智能学院

山东大学

济南, 山东省

✉ whb0826@sdu.edu.cn

武寒波，博士，正高级工程师，山东大学浪潮人工智能学院助理教授。博士毕业于山东大学控制科学与工程学院。主持国家自然科学基金青年项目、山东省自然科学基金青年项目，参与多项国家重点研发计划、山东省自然科学基金重大基础研究项目。迄今已在中科院SCI-1区期刊IEEE TMM、TCSVT等发表论文十余篇。授权发明专利4项。研究兴趣主要包括计算机视觉、模式识别、视频人体行为识别、大模型、具身智能等。

随时欢迎具有人工智能或者大模型基础，以及对视频理解、智能人机交互、具身智能感兴趣的老师/本科生/实习生通过邮件whb0826@sdu.edu.cn或者微信联系交流合作。

📖 工作经历

2025.08 ~ 至今助理教授, 人工智能学院, 山东大学
2024.07 ~ 2025.05正高级工程师, 山东浪潮科学研究院, 研究聚焦领域LLM继续预训练与微调
2022.06 ~ 2024.07博士后, 山东大学, 研究聚焦行为识别、疾病AI辅助诊断

🔥 最新消息

[2025.05] 1篇论文被期刊Engineering Applications of Artificial Intelligence (SCI Q1 TOP)接收!

[2025.01] 1篇论文被期刊Expert Systems With Applications (SCI Q1 TOP)接收!

[2024.11] 1篇论文被期刊Signal Processing: Image Communication (SCI Q2)接收!

[2024.08] 1篇论文被期刊Knowledge-Based Systems (SCI Q1 TOP)接收!

[2024.06] 1篇论文被期刊Pattern Recognition (SCI Q1 TOP)接收!

[2024.06] 1篇论文被期刊Neurocomputing (SCI Q2)接收!

[2023.02] 1篇论文被期刊Signal Processing: Image Communication (SCI Q2)接收!

[2022.03] 1篇论文被期刊IEEE Transactions on Circuits and Systems for Video Technology (SCI Q1 TOP)接收, ESI Highly Cited Paper!

📝 发表论文

Semantic-guided modeling of spatial relation and object co-occurrence for indoor scene recognition. Chuanxin Song, Hanbo Wu, Xin Ma. Expert Systems with Applications, 2025.
Enhancing autism spectrum disorder early detection with parent-child dyads block-play protocol and attention-enhanced hybrid deep learning framework. Xiang Li, Lizhou Fan, Hanbo Wu, Kunping Chen, Xiaoxiao Yu, Chao Che, Zhifeng Cai, Xiuhong Niu, Aihua Cao, Xin Ma. Engineering Applications of Artificial Intelligence, 2025.
Transformer-based multiview spatiotemporal feature interactive fusion for human action recognition in depth videos. Hanbo Wu, Xin Ma, Yibin Li. Signal Processing: Image Communication, 2024.
Dual-View Spatio-Temporal Interactive Network for Video Human Action Recognition. Hanbo Wu, Xin Ma. In Proceedings of the 17th International Conference on Intelligent Robotics and Applications, 2024.
Semantic-embedded similarity prototype for scene recognition. Chuanxin Song, Hanbo Wu, Xin Ma, Yibin Li. Pattern Recognition, 2024.
Inter-object discriminative graph modeling for indoor scene recognition. Chuanxin Song, Hanbo Wu, Xin Ma. Knowledge Based Systems, 2024.
Multi-scale sampling attention graph convolutional networks for skeleton-based action recognition. Haoyu Tian, Yipeng Zhang, Hanbo Wu, Xin Ma, Yibin Li. Neurocomputing, 2024.
Multi-level channel attention excitation network for human action recognition in videos. Hanbo Wu, Xin Ma, Yibin Li. Signal Processing: Image Communication, 2023.
Spatiotemporal Multimodal Learning with 3D CNNs for Video Action Recognition. Hanbo Wu, Xin Ma, Yibin Li. IEEE Transactions on Circuits and Systems for Video Technology, 2022. (ESI Highly Cited Paper)
Skeleton-based abnormal gait recognition with spatio-temporal attention enhanced gait-structural graph convolutional networks. Haoyu Tian, Xin Ma, Hanbo Wu, Yibin Li. Neurocomputing, 2022.
Convolutional Networks With Channel and STIPs Attention Model for Action Recognition in Videos. Hanbo Wu, Xin Ma, Yibin Li. IEEE Transactions on Multimedia, 2020.
Hierarchical dynamic depth projected difference images–based action recognition in videos with convolutional neural networks. Hanbo Wu, Xin Ma, Yibin Li. International Journal of Advanced Robotic Systems, 2019.
Collecting public RGB-D datasets for human daily activity recognition. Hanbo Wu, Xin Ma, Yibin Li. International Journal of Advanced Robotic Systems, 2017.

📝 授权专利

基于双视角时空交互网络的视频行为识别方法及系统
基于层次动态深度投影差值图像表示的视频行为识别方法及系统
一种深度视频行为识别方法及系统
基于通道注意力导向时间建模的视频行为识别方法及系统

🏆 荣誉奖励

2023《基于深度学习的行为识别关键技术及应用》“国际先进水平”
2021山东省研究生优秀成果奖
2021山东大学研究生优秀学术成果奖