YU, Tianshu (to join in Fall 2021)

Assistant Professor

Education Background

Ph.D. in Computer Science, Arizona State University, 2021

M.Sc. in Geomatics Engineering, University of Calgary, 2016

B.Sc. in Computer Science, Shenyang University of Technology, 2012

Research Field
Machine Learning, Optimization of Combinatorial Problems, Optimization and Learning of Graph, RNNs and Determinantal Point Process
Biography

Dr. Tianshu Yu will join the Chinese University of Hong Kong, Shenzhen as an Assistant Professor in Fall 2021. Professor Yu received bachelor degree in Computer Science at Shenyang University of Technology in 2012, master degree in Geomatics Engineering from Calgary University in 2016. Prior to that, he worked as an algorithm engineer in Philips Healthcare from 2012 to 2014. He has been a PhD student in computer science at Arizona State University since 2017.

His research interest covers several aspects in machine learning and optimization of combinatorial problems. He is particularly interested in investigating modeling, optimization and learning of graph, and seeking the structural extension within deep learning framework. He also conducts research on RNNs and determinantal point process. Dr. Yu has also served as a reviewer for several top conferences (e.g., ICLR 2021, NIPS 2020, CVPR 2019-2021, ICCV 2019, ECCV 2020) and invited reviewers for top journals (e.g., IEEE Transactions on Image Processing, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Circuits and Systems for Video Technology, Pattern Recognition, Pattern Recognition Letters).

Academic Publications

1. Tianshu Yu*, Yikang Li*, Baoxin Li. RhyRNN: Rhythmic RNN for Recognizing Events in Long and Complex Videos. ECCV2020 (*equal contribution)

2. Tianshu Yu, Junchi Yan, Baoxin Li. Determinant Regularization for Gradient-Efficient Graph Matching. CVPR2020

3. Tianshu Yu, Runzhong Wang, Junchi Yan, Baoxin Li. Learning Deep Graph Matching via Channel-Independent Embedding and Hungarian Attention. ICLR2020

4. Tianshu Yu, Yikang Li, Baoxin Li. Deep Learning of Determinantal Point Processes via Proper Spectral Sub-gradient. ICLR2020

5. Tianshu Yu, Junchi Yan, Yilin Wang, Wei Liu, Baoxin Li. Generalizing graph matching beyond quadratic assignment model. NeurIPS2018

6. Yikang Li*, Tianshu Yu*, Baoxin Li. Simultaneous event localization and recognition for surveillance video. AVSS2018 (*equal contribution)      

7. Tianshu Yu, Junchi Yan, Wei Liu, Baoxin Li. Incremental multi-graph matching via diversity and randomness based graph clustering. ECCV2018

8. Tianshu Yu, Junchi Yan, Jieyi Zhao, Baoxin Li. Joint cuts and matching of partitions in one graph. CVPR2018

9. Zhiyuan Fang, Shu Kong, Tianshu Yu, Yezhou Yang. Weakly Supervised Attention Learning for Textual Phrases Grounding. CVPR2018 workshop

10. Tianshu Yu, Ruisheng Wang. Enhancing scene parsing by transferring structures via efficient low-rank graph matching. ACM SIGSPATIAL2016

11. Tianshu Yu, Ruisheng Wang. Graph matching with low-rank regularization. WACV2016

12. Tianshu Yu, Ruisheng Wang. Scene parsing using graph matching on street-view data. CVIU 145:70-80, 2016

13. Hong Shao, Shuang Chen, Jieyi Zhao, Wencheng Cui, Tianshu Yu. Face recognition based on subset selection via metric learning on manifold. FITEE 16:1046-1058, 2015

14. Tianshu Yu*, Hong Shao*, Mengjia Xu, Wencheng Cui. Image region duplication detection based on circular window expansion and phase correlation. Forensic Science International 222:71-82, 2012 (*equal contribution)