徐衍钰，研究员，泰山学者青年专家，山东大学齐鲁青年。本科毕业于大连理工大学，博士毕业于中国科学院大学，2020年11月至2024年06月在新加坡科技研究局高性能计算所（IHPC, A*STAR）担任研究员。主要从事计算机视觉，图像和视频理解、医学影像分析、机器学习等方面的研究工作，主持泰山学者青年专家支持计划、齐鲁青年学者计划等项目，以及多项新加坡科技研究局科研项目。在IEEE TPAMI、IEEE TIP、IEEE TCSVT、CVPR、ICCV、NeurIPS、ECCV等国际高水平期刊和顶级会议上发表学术论文20余篇，中国专利1项。 长期担任IEEE TPAMI、TNNLS、TCSVT、TMI、TMM等国际期刊审稿人以及ICML/CVPR/ICCV/ECCV/IJCAI/AAAI/ICLR等人工智能顶级会议审稿人。2024年入选“齐鲁青年学者”，入选“泰山学者青年专家”。

研究方向：

计算机视觉，图像和视频理解、医学影像分析、机器学习等方面的研究工作。

针对平面、全景图像视频等数据类型，分别提出了个体信息编码的个性化显著性分析模型、语言描述编码的街景主目标定位模型和新型球状卷积的群体主动显著性分析模型

针对数据利用率较低的问题，基于图像纹理的相似性，定义了新颖的部分监督学习范式，并分别提出了样本筛选的主动学习模型、全局记忆模块的部分监督模型和自监督特征的伪标签生成弱监督模型

参数高效微调：不同于传统的低秩角度，这个工作从控制的角度出发分析，并提出一种非线性控制器

招生方向：
欢迎有意向攻读人工智能、软件工程的硕士生联系我，请在邮件附上简历；课题组与香港大学、上海科技大学、新加坡南洋理工大学、新加坡国立大学、新加坡科技研究局等多个国际一流科研团队始终保持着密切合作，为组内学生提供良好的国内外交流机会。课题组长期接收山东大学本科生进课题组进行科研训练，有兴趣的同学请邮件联系xu_yanyu@sdu.edu.cn

[Google Scholar]: https://scholar.google.com/citations?user=Y3hU1AYAAAAJ&hl=en

主持项目：

1. 泰山学者工程，（2024-2026）, 主持；

2. 齐鲁青年学者支持计划，（2024-2029），主持；

3. “一种资源高效学习的框架：加速医学图像分析技术从封闭到开放环境应用的开发和部署”，（2024.01-2024.06），新加坡科技研究局，主持；

4. “基于深度学习辅助社区白内障筛查的便携式摄像装置”，（2023-2024），新加坡科技研究局，参与；

5. “基于少标注学习的用于医疗应用的新型双变换器方法”，（2022-2023），新加坡科技研究局，主持；

代表论文和期刊：

1. Yanyu Xu, Yingzhi Xia, Huazhu Fu, Rick Goh, Yong Liu, Xinxing Xu, ``Multi-scale Region-aware Implicit Neural Network for Medical Images Matting", MICCAI 2024. (CCF-B)

2. Menghan Zhou, Yanyu Xu*, Zhi Da Soh, Huazhu Fu, Rick Goh, Chingyu Cheng, Yong Liu, and Liangli Zhen, ``MedMLP: An Efficient MLP-like Network for Zero-shot Retinal Image Classification", MICCAI 2024. (CCF-B)

3. Ziming Zhong, Yanyu Xu, Jing Li, Jiale Xu, Zhengxin Li, Chaohui Yu, and Shenghua Gao, ``MeshSegmenter: Zero-Shot Mesh Segmentation via Texture Synthesis", ECCV 2024. (CCF-B)

4. Chi Zhang, Cheng Jingpu, Yanyu Xu, Qianxiao Li, ``Parameter-Efficient Fine-Tuning with Controls", ICML 2024. (CCF-A)

5. Yanyu Xu, Menghan Zhou, Yangqin Feng, Xinxing Xu, Huazhu Fu, Rick Goh, Yong Liu, ``Minimal-supervised Medical Image Segmentation via Vector Quantization Memory'', MICCAI 2023. (CCF-B)

6. Chi Zhang, Zhang Xiaoman, Ekanut Sotthiwat, Yanyu Xu, Ping Liu, Liangli Zhen, Yong Liu, ``Generative Gradient Inversion Without Prior'', ICCV 2023. (CCF-A)

7. Yanyu Xu, Ziheng Zhang, Shenghua Gao, ``Spherical DNNs and Their Applications in 360∘ Images and Videos'', IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022, 44(10): 7235-7252. (CCF-A)

8. Yanyu Xu, Ziming Zhong, Dongze Lian, Jing Li, Zhengxin Li, Xinxing Xu, and Shenghua Gao. ``Crowd Counting With Partial Annotations in an Image'', Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 15570-15579. (CCF-A)

9. Yanyu Xu, Xinxing Xu, Lei Jin, Shenghua Gao, Rick Goh, Daniel Ting and Yong Liu, ``Partial-supervised Learning for Vessel Segmentation in Ocular Images''. Medical Image Computing and Computer Assisted Interventions,  2021. (CCF-B)

10. Yuting Xiao, Yanyu Xu, Ziming Zhong, Weixin Luo, Jiawei Li, and Shenghua Gao, ``Amodal Segmentation Based on Visible Region Segmentation and Shape Prior'', AAAI Conference on Artificial Intelligence, 2021. (CCF-A)

11. Jiale Xu, Jia Zheng, Yanyu Xu, Rui Tang and Shenghua Gao: ``Layout-Guided Novel View Synthesis from a Single Indoor Panorama". IEEE Conference on Computer Vision and Pattern Recognition, 2021. (CCF-A)

12. Zibo Zhao, Wen Liu, Yanyu Xu, Xianing Chen, Weixin Luo, Lei Jin, Bohui Zhu, Tong Liu, Binqiang Zhao, and Shenghua Gao, ``Prior Based Human Completion'', IEEE Conference on Computer Vision and Pattern Recognition, 2021. (CCF-B)

13. Yanyu Xu, Zhixin Piao, Wen Liu, Ziheng Zhang, and Shenghua Gao: ``SUNNet: A Novel Framework for Simultaneous Human Parsing and Pose Estimation", Neurocomputing, 2021, 444: 349-355.

14. Peiyao Wang, Weixin Luo, Yanyu Xu, Shugong Xu, Jianyu Yang and Shenghua Gao: ``SIRI-SDR: SpatIal Relation Induced Spatial Description Resolution". Advances in Neural Information Processing Systems, 2020. (CCF-A)

15. Lei Jin*, Yanyu Xu*, Jia Zheng, Junfei Zhang, Rui Tang, Jingyi Yu and Shenghua Gao: ``Geometric Structure Based and Regularized Depth Estimation From 360$\degree$ Indoor Imagery". IEEE Conference on Computer Vision and Pattern Recognition, 2020: 889-898. (CCF-A)

16. Yanyu Xu, Shenghua Gao, Junru Wu, Nianyi Li and Jingyi Yu, ``Beyond Universal Saliency: Personalized Saliency and its Prediction", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019. (CCF-A)

17. Yanyu Xu, Yanbing Dong, Junru Wu, Zhengzhong  Sun, Zhiru  Shi, Jingyi Yu and Shenghua Gao: ``Gaze Prediction in Dynamic $360^\circ$ Immersive Videos", IEEE Conference on Computer Vision and Pattern Recognition, 2018: 5333-5342. (CCF-A)

18. Yanyu Xu, Zhixin Piao, and Shenghua Gao: ``Encoding Crowd Interaction with Deep Neural Network for Pedestrian Trajectory Prediction'', IEEE Conference on Computer Vision and Pattern Recognition, 2018: 5275-5284. (CCF-A)

19. Quan Chen, Tiezheng Ge, Yanyu Xu, Zhiqiang Zhang, and Kun Gai, ``Human Semantic Matting'', ACM International Conference on Multimedia, 2018: 618-626. (CCF-A)

20. Ziheng Zhang*, Yanyu Xu*, Jinyi Yu, and Shenghua Gao, ``Saliency Detection in $360^\circ$ Videos'', European Conference on Computer Vision, 2018: 488-503. (CCF-B)

21. Yanyu Xu, Nianyi Li, Junru Wu, Jingyi Yu, and Shenghua Gao, ``Beyond Universal Saliency: Personalized Saliency Prediction with Multi-task CNN", In Proceedings of the International Joint Conference on Artificial Intelligence, 2017: 3887-3893. Outstanding Student Paper Runner-up, (CCF-A)