Scholar
Shiyu Zhao (赵世雨)
Google Scholar ID: M-qzlU8AAAAJ
PhD student of Computer Scicence, Rutgers University
Citations & Impact
Citations
1,218
H-index
13
i10-index
16
Publications
20
Co-authors
12
list available
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction (CVPR, 2025)
- Generating Enhanced Negatives for Training Language-Based Object Detectors (CVPR, 2024)
- Taming Self-Training for Open-Vocabulary Object Detection (CVPR, 2024)
- Exploiting Unlabeled Data with Vision and Language Models for Object Detection (ECCV, 2022)
- Global Matching with Overlapping Attention for Optical Flow Estimation (CVPR, 2022)
- Deep Animation Video Interpolation in the Wild (CVPR, 2021)
- RefineDNet: A Weakly Supervised Refinement Framework for Single Image Dehazing (Transactions on Image Processing, 2021)
- Dehazing Evaluation: Real-world Benchmark Datasets, New Criteria and Baselines (Transactions on Image Processing, 2020)
- A CNN-based Depth Estimation Approach with Multi-scale Sub-pixel Convolutions and A Smoothness Constraint (ACCV, 2018)
Research Experience
- Research intern/student researcher at Meta/Google/NEC Labs/SenseTimes working on Generative Models, Multi-modality Models, LLMs, Vision-and-Language Models, and Image Understanding.
Education
- Received B.S. in 2017 and M.S. in 2020 from the School of Software Engineering at Tongji University, supervised by Prof. Lin Zhang; currently pursuing a PhD degree in the Department of Computer Science at Rutgers University, supervised by Prof. Dimitris Metaxas.
Background
- Research interest: Solving computer vision problems with large foundation models. Research intern/student researcher at Meta/Google/NEC Labs/SenseTimes on Generative Models/Multi-modality Models/LLMs/Vision-and-Language Models/Image Understanding.
Miscellany
- Actively looking for a full-time position in Industry.
