About me

Welcome to my academic homepage! My name is Wenyu Zhang, and I am a Ph.D. student at the School of Computer Science, University of Science and Technology of China (USTC). Under the guidance of Prof. Xinming Zhang, my research focuses on the applications of graph neural networks in computer vision.

My current research aims to explore the potential of graph neural networks (GNNs) for solving various computer vision problems, such as Person Re-identification, Point cloud analysis, and Video understanding. GNNs are a powerful tool for modeling and analyzing complex graph-structured data, and they hold great promise for advancing the state of the art in computer vision.

I am excited to be a part of the vibrant research community at USTC, and I look forward to collaborating with other researchers in the field to make meaningful contributions to computer vision and machine learning. Thank you for visiting my academic homepage, and please feel free to reach out to me if you have any questions or would like to discuss potential collaborations.

Publication

[1] Wenyu Zhang, Xin Deng, Baojun Jia, Xingtong Yu, Yifan Chen, Jin Ma, Qing Ding, Xinming Zhang. Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution. The 31th ACM International Conference on Multimedia (ACM MM), 2023, Accept, paper, code.

[2] Xin Deng, Wenyu Zhang (Co-first author), Qing Ding, Xinming Zhang. PointVector: A Vector Representation In Point Cloud Analysis. In Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023, Accept, paper, code.

[3] Mingyue Cheng, Qi Liu, Wenyu Zhang, Zhiding Liu, Hongke Zhao, Enhong Chen. A General Tail Item Representation Enhancement Framework for Sequential Recommendation. Front. Comput. Sci., 2023, https://doi.org/10.1007/s11704-023-3112-y

[4] Wenyu Zhang, Qing Ding, Jian Hu, Yi Ma, Mingzhe Lu. Pixel-wise Graph Attention Networks For Person Re-identification. *The 29th ACM International Conference on Multimedia (ACM MM), 2021, Accept, paper, code.