I am now a Research Fellow at City University of Hong Kong. Before that, I received my Ph.D. degree in Computer Science at City University of Hong Kong (CityU) supervised by Prof. LIAO Jing in 2023. I was a remote visiting PhD student with Prof. Saining Xie at NYU in 2023 for 8 months. I obtained my B.Eng. degree in Computer Science and Technology (Elite Program) at South China University of Technology (SCUT) advised by Prof. Shengfeng He.

Research

My research interests focus on computer vision, graphics and machine learning, especially for multimodal (text, 2D, 3D, and 4D), creative, and human-aligned AI. Specifically, I am exploring the integration of human-aligned priors, learning strategies, multi-modal knowledge, and scalable-generalizable guidance, to both examine and enhance these models. In particular, on topics:

• Learning on Imperfect 3D and Multimodal Data
• Human-aligned Multimodal Perception, Reasoning, Benchmarks
• 3D and 4D Generation and Perception
• 2D Vision on Medical and Inconspicuous Image

Education

• 02/2023 ~ 10/2023: Remote Visiting Student, Computer Science, New York University, supervised by Prof. Saining Xie.
• 08/2019 ~ 08/2023: PhD student, Department of Computer Science, City University of Hong Kong, supervised by Prof. LIAO Jing.
• 09/2015 ~ 07/2019: Computer Science and Technology (Elite Program), South China University of Technology, advised by Prof. Shengfeng He.

Experience

• 09/2024 ~ 02/2025: Research Fellow at City University of Hong Kong.
• 10/2023 ~ 08/2024: Postdoctoral Researcher at City University of Hong Kong.
• 07/2022 ~ 11/2022: Research Internship at Microsoft Cloud & AI, Microsoft Research, Redmond, United States, mentored by Dr. Yujia Xie, advised by Dr. Dongdong Chen, Dr. Yichong Xu.

Do Multimodal Large Language Models See Like Humans?

Jiaying Lin^#, Shuquan Ye^#, Rynson W.H. Lau.
arXiv Preprint.
[project] [arxiv] [paper] [code]
^#Equal Contribution

Leveraging RGB-D Data with Cross-Modal Context Mining for Glass Surface Detection

Jiaying Lin^#, Yuen-Hei Yeung^#, Shuquan Ye, Rynson W.H. Lau.
Thirty-Ninth Conference AAAI Conference on Artificial Intelligence (AAAI), 2025.
[project] [arxiv] [paper] [code]
^#Equal Contribution

Learning a Single Network for Robust Medical Image Segmentation With Noisy Labels

Shuquan Ye, Yan Xu, Dongdong Chen, Songfang Han, Jing Liao.
IEEE Transactions on Medical Imaging (TMI), 2024
[paper]

Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles

Shuquan Ye, Yujia Xie, Dongdong Chen, Yichong Xu, Lu Yuan, Chenguang Zhu, Jing Liao.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 (Highlight).
[project] [arxiv] [code]

Robust Point Cloud Segmentation with Noisy Annotations

Shuquan Ye, Dongdong Chen, Songfang Han, Jing Liao.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2022 IF: 24.314.
[project] [paper] [code]

3D Question Answering

Shuquan Ye, Dongdong Chen, Songfang Han, Jing Liao.
IEEE Transactions on Visualization and Computer Graphics (TVCG, CCF A, JCR Q1) 2022.
[project] [early access] [arxiv] [code and dataset] [talks]with 2000 audiences

Exemplar-Based 3D Portrait Stylization

Fangzhou Han^#, Shuquan Ye^#, Mingming He, Menglei Chai, Jing Liao.
IEEE Transactions on Visualization and Computer Graphics (TVCG, CCF A, JCR Q1) 2021.
[project] [paper] [code]
^#Equal Contribution

Learning with Noisy Labels for Robust Point Cloud Segmentation

Shuquan Ye, Dongdong Chen, Songfang Han, Jing Liao.
International Conference on Computer Vision (ICCV) 2021, (Oral).
[project] [paper] [code]

Meta-PU An Arbitrary-Scale Upsampling Network for Point Cloud

Shuquan Ye, Dongdong Chen, Songfang Han, Ziyu Wan, Jing Liao.
IEEE Transactions on Visualization and Computer Graphics (TVCG, CCF A, JCR Q1), 2021.
[paper] [code]

Coherence and Identity Learning for Arbitrary-length Face Video Generation

Shuquan Ye, Chu Han, Jiaying Lin, Guoqiang Han, Shengfeng He.
International Conference on Pattern Recognition (ICPR), 2020.
[paper]

Two-dimensional-reduction Random Forest

Shuquan Ye, Zhiwen Yu, Jiaying Lin, Kaixiang Yang, Dan Dai, Zhi-Hui Zhan, Wei-Neng Chen, Jun Zhang.
International Conference on Information Science and Technology (ICIST), (Oral), 2018.
[paper]

Journal Reviewing:

• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
• ACM Transactions on Graphics (TOG).
• IEEE Transactions on Visualization and Computer Graphics (TVCG).
• IEEE Transactions on Multimedia (TMM).
• International Journal of Computer Vision (IJCV).
• IEEE Journal of Biomedical and Health Informatics (JBHI).
• Pattern Recognition.
• International Journal of Applied Earth Observation and Geoinformation (JAG).
• IEEE Access.
• IEEE Geoscience and Remote Sensing Letters (GRSL).
• Computational and Mathematical Methods in Medicine.

Conference Reviewer:

• CVPR 2023, CVPR 2022, ECCV 2022.

Teaching Assistant at CityU

• Database System (CS3402)

Awards

• Research Tuition Scholarship, City University of Hong Kong, 2022 - 2023
• Research Tuition Scholarship, City University of Hong Kong, 2021 - 2022
• Postgraduate Scholarship, City University of Hong Kong, 2019 - 2022
• Student Scholarship, South China University of Technology, 2015 - 2019
• Elite Student Program, South China University of Technology (Top 0.4%), 2015 - 2019

My first cosplay ever as my favorite character, Mutsumi Wakaba...

Album
Special thanks to Jiaying Lin.