Skip to the content.
Shiyu Zhao 赵世雨

Rutgers University

sz553@rutgers.edu

I received B.S. and M.S. in 2017 and 2020, respectively, in the School of Software Engineering at Tongji University with the supervision of Prof. Lin Zhang. Currently, I’m pursuing the PhD degree in the Department of Computer Science at Rutgers University with the supervision of Prof. Dimitris Metaxas. My research interest lies in solving computer vision problems with large foundation models. See my research in google scholar or below.

I was research interns/student researchers at Meta/Google/NEC Labs/SenseTimes on Generative Models/Multi-modality Models/LLMs/Vision-and-Language Models/Image Understanding.

I’m actively looking for a full-time position at Industry. Here is my resume.

Selected Publications & Projects

(* indicates equal contributions)

Accelerating Multimodel Large Language Models by Searching Optimal Vision Token Reduction
Shiyu Zhao, Zhenting Wang, Felix Juefei-Xu, Xide Xia, Miao Liu, Xiaofang Wang, Mingfu Liang, Ning Zhang, Dimitris N. Metaxas, Licheng Yu
Technical report
Paper, Code (Coming)
Generating Enhanced Negatives for Training Language-Based Object Detectors
Shiyu Zhao, Long Zhao, Vijay Kumar B.G, Yumin Suh, Dimitris N. Metaxas, Manmohan Chandraker, Samuel Schulter
In CVPR 2024
Paper, Code
Taming Self-Training for Open-Vocabulary Object Detection
Shiyu Zhao, Samuel Schulter, Long Zhao, Zhixing Zhang, Vijay Kumar B.G, Yumin Suh, Manmohan Chandraker, Dimitris Metaxas
In CVPR 2024
Paper, Code
Exploiting Unlabeled Data with Vision and Language Models for Object Detection
Shiyu Zhao*, Zhixing Zhang*, Samuel Schulter, Long Zhao, Vijay Kumar B.G, Anastasis Stathopoulos, Manmohan Chandraker, Dimitris Metaxas
In ECCV, 2022
Paper, Poster, Code, Website
Global Matching with Overlapping Attention for Optical Flow Estimation
Shiyu Zhao, Long Zhao, Zhixing Zhang, Enyu Zhou, Dimitris Metaxas
In CVPR, 2022
Paper, Code
Deep Animation Video Interpolation in the Wild
Li Siyao, Shiyu Zhao, Weijiang Yu, Wenxiu Sun, Dimitris Metaxas, Chen Change Loy, and Ziwei Liu
In CVPR, 2021
Paper, Code
RefineDNet: A Weakly Supervised Refinement Framework for Single Image Dehazing
Shiyu Zhao, Lin Zhang, Ying Shen, and Yicong Zhou
Transactions on Image Processing, 2021
Paper, Code
Dehazing Evaluation: Real-world Benchmark Datasets, New Criteria and Baselines
Shiyu Zhao, Lin Zhang, Shuaiyi Huang, Ying Shen, and Shengjie Zhao
Transactions on Image Processing, 2020
Paper, Code

A CNN-based Depth Estimation Approach with Multi-scale Sub-pixel Convolutions and A Smoothness Constraint
Shiyu Zhao, Lin Zhang, Ying Shen, and Yongning Zhu
In ACCV, 2018
Paper, Code