Jing Yu Koh
Before joining Google, I was an undergrad at the Singapore University of Technology and Design. I graduated with Summa Cum Laude (highest honors) in 2019.
- (July 2021) 1 paper accepted to ICCV 2021!
- (July 2021) Presenting an invited talk at Microsoft Research.
- (March 2021) 1 paper accepted to CVPR 2021!
- (January 2021) 1 paper accepted to ICLR 2021!
- (October 2020) 1 paper accepted to WACV 2021!
- (July 2020) 1 paper accepted to ECCV 2020!
- (October 2019) Officially joined Google Research in Mountain View, California.
Publications [Google Scholar]
H. Zhang*, J.Y. Koh*, J. Baldridge, H. Lee, Y. Yang, "Cross-Modal Contrastive Learning for Text-to-Image Generation", in CVPR, June 2021. (* denotes equal contribution)
W. Lee, W. Jung, H. Zhang, T. Chen, J.Y. Koh, T. Huang, H. Yoon, H. Lee, and S. Hong, "Revisiting hierarchical approach for persistent long-term video prediction", in ICLR, May 2021.
J.Y. Koh, J. Baldridge, H. Lee, Y. Yang, "Text-to-Image Generation Grounded by Fine-Grained User Attention", in The IEEE Winter Conference on Applications of Computer Vision (WACV)., January 2021.
S. Ghosh*, J.Y. Koh*, and P. Jaillet, "Improving customer satisfaction in bike sharing systems through dynamic repositioning", IJCAI, August 2019. (* denotes equal contribution).
G. Goh, J.Y. Koh, and Y. Zhang, "Twitter-informed Crowd Flow Prediction", IEEE International Conference on Data Mining (ICDM) Workshops, November 2018.
T.Feng, Q.-T. Truong, D.T. Nguyen, J.Y. Koh, L.-F. Yu, A. Binder, and S.-K. Yeung, " Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data" in ECCV, September 2018.
Model Zoo curates pre-trained deep learning models and code, making it easy for researchers to find models for various frameworks.
Web application that provides readers with book recommendations for a selected genre.
The CNY Yusheng app is a reference app designed to help you learn more about unique Chinese New Year traditions and the yusheng dish.
Decision making app for iOS that allows you to objectively evaluate and analyze each choice.