One paper accepted at CVPR 2025.
Researcher · Computer Vision · Generative Models
Zhenyao Wu
Working at the intersection of generative image editing, graphic generative models, multimodal models, low-level vision, and robust visual understanding.
About
Research built around practical visual intelligence.
I am currently a researcher at Honor Device Co., Ltd.. My research interests include generative image editing, graphic generative models, multimodal models, and low-level vision.
Before joining Honor, I received my Ph.D. degree from University of South Carolina under the supervision of Prof. Song Wang and Prof. Lili Ju in 2022. Before that, I received my B.S. in College of Intelligence and Computing from Tianjin University in 2018.
I am looking for full-time researchers and interns on low-level vision, graphic generative models, and multimodal models. Feel free to send me an email if you are interested.
News
Recent updates
Two papers accepted at AAAI 2023.
Four papers accepted at ECCV 2022.
One paper accepted at ACMMM 2022.
One paper accepted at TPAMI.
Selected Publications
Vision, adaptation, saliency, and depth.
AAAI 2020
SalSAC: A Video Saliency Prediction Model with Shuffled Attentions and Correlation-based ConvLSTM
Xinyi Wu, Zhenyao Wu, Jinglin Zhang, Lili Ju, Song Wang.
PDF
Experience & Service
Academic and industry practice.
Internships
Applied Scientist Intern, Amazon, New York, NY. May-Nov, 2021. Worked with Sonny Hu, Dr. Amit Agrawal, and Dr. Larry Davis.
Service
Program Committee/Reviewer: CVPR(2020/2021/2022/2023), ICCV(2021), ECCV(2022), AAAI(2020/2021/2022/2023), NeurIPS(2020/2021/2022/2023), ICLR(2021), IJCAI(2022), ACMMM(2022), WACV(2020/2021), ACCV(2020), IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Multimedia, IEEE Transactions on Image Processing, Pattern Recognition Letters, IET Computer Vision.
Get In Touch