Shuyan LiPostdoctoral Research Associate Department of Engineering, University of Cambridge Email: sl2141@cam.ac.uk |
|
Biography
I am currently a Postdoctoral Research Associate in Department of Engineering at University of Cambridge, working with Prof. Ioannis Brilakis. My role is to lead a work package of BIM2TWIN project, funded by European Commission H2020. I am broadly interested in computer vision and machine learning. My current research focuses on representation learning, point cloud processing and transfer learning.
In Jan. 2022, I got my doctor’s degree in the Department of Automation at Tsinghua University, Intelligent Vision Group(IVG). I was supervised by Prof. Jiwen Lu , Prof. Jie Zhou and Prof. Xiu Li .
News
2023-02: 3 papers on domain adaptation, object detection and multi-modal learning were accepted by ICASSP’2023.
2023-01: My doctorate thesis was awarded as Excellent Doctorate Dissertation by ShenZhen Association for Artificial Intelligence (3 people awarded per annual).
2023-01: I gave a seminar talk at Division D, Department of Engineering at University of Cambridge to introduce unsupervised learning for digital twins. Thanks Prof. Ioannis Brilakis for the invitation!
2022-11: 1 paper on transfer learning was accepted by AAAI’2023 as oral presentation.
2022-10: I started a role as a Postdoctoral Research Associate in Department of Engineering, University of Cambridge.
2022-02: I got an Athena Post-Doctoral Fellowship funded by NSF.
2021-06: 1 paper on video hashing was accepted by IEEE TCSVT.
2021-03: 1 paper on video hashing was accepted by CVPR’2021.
Publications
|
Qiaosong Chu, Shuyan Li, Guangyi Chen, Kai Li and Xiu Li Association for the Advancement of Artificial Intelligence (AAAI), 2023 [PDF] [Video] [Code] We propose an adversarial learning based source free object detection method. |
|
Shuyan Li, Xiu Li, Jiwen Lu and Jie Zhou IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021 [PDF] This is the journal version of NPH. Compared with NPH, we further develop an encoding network that can capture the hierachical structure of a video. |
|
Shuyan Li, Xiu Li, Jiwen Lu and Jie Zhou IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 [PDF] [Code] We propose a self-supervised learning framework to capture bidirectional correlations among videos based on transformers. |
|
Shuyan Li, Zhixiang Chen, Jiwen Lu, Xiu Li, and Jie Zhou IEEE International Conference on Computer Vision (ICCV), 2019 [PDF] We learn video hash functions via exploiting the neighborhood structure among videos. |
|
Shuyan Li, Zhixiang Chen, Xiu Li, Jiwen Lu, and Jie Zhou IEEE Transactions on Multimedia (TMM), 2020 [PDF] We propose a variational mechanism to learn robust video hash representation. |
Teaching
Demonstrator & Marking, 3F8: Inference, Department of Engineering, University of Cambridge, Lent term 2023
TA, Computer culture basis, awarded as “Outstanding TA”, Tsinghua University, Fall 2020
Teacher, Music, Central elementary school in Huangtu Town, Guizhou Province, Summer 2021
Academic Services
Conference Reviewer: AAAI, ICASSP, ICME, PRCV, WACV, ICIP, etc.
Journal Reviewer: IEEE/ACM TASLP, IEEE TIP, IEEE TMM, IEEE TCSVT, PR, Neuralcomputing, etc.
| © Shuyan Li | Last updated: Feb., 2023 |