Biography
My research interests mainly include machine learning and weakly supervised learning.
Currently, I am an assistant researcher (至善博后) at the PALM Group ,
School of Computer Science and Engineering,
Southeast University, China. I received the Ph.D. degree from Southeast University, China, in 2025, advised by Prof. Hui Xue.
Seletected Publication
- Shipeng Zhu, Hui Xue, Na Nie, Chenjie Zhu, Haiyue Liu, Pengfei Fang. Reproducing the Past: A Dataset for Benchmarking Inscription Restoration.
In: Proceedings of the 32nd ACM International Conference on Multimedia (ACM MM'24), 7714-7723, Melbourne, Australia, 2024. (CCF-A, Best Paper Nomination)
- Shipeng Zhu, Pengfei Fang, Chenjie Zhu, Zuoyan Zhao, Qiang Xu, Hui Xue. Text Image Inpainting via Global Structure-Guided Diffusion Models.
In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI'24), 38(7): 7775-7783, Vancouver, Canada, 2024. (CCF-A)
- Shipeng Zhu, Zuoyan Zhao, Pengfei Fang, Hui Xue. Improving Scene Text Image Super-resolution via Dual Prior Modulation Network.
In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI'23), 37(3): 3843-3851, Washington DC, USA, 2023. (CCF-A)
- Shipeng Zhu, Jun Fang, Pengfei Fang, Hui Xue. Improving Scene Text Retrieval via Stylized Middle Modality.
ACM Transactions on Multimedia Computing, Communications, and Application (ToMM'24), 20(12): 1-18, 2024. (CCF-B)
- Zuoyan Zhao, Hui Xue, Pengfei Fang, Shipeng Zhu. PEAN: A Diffusion-Based Prior-Enhanced Attention Network for Scene Text Image Super-Resolution.
In: Proceedings of the 32nd ACM International Conference on Multimedia (ACM MM'24), 9769-9778, Melbourne, Australia, 2024. (CCF-A)
- Yangfang Xue, Pengfei Fang, Jinyue Tian, Shipeng Zhu, Hui Xue. CosNet: A Generalized Spectral Kernel Network.
In: Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS'23), 36: 37273-37285, New Orleans, USA, 2023. (CCF-A)
- Pengfei Fang, Yaojun Hu, Shipeng Zhu, Hui Xue. On Learning Distribution Alignment for Video-based Visible-infrared Person Re-identification.
Computer Vision and Image Understanding (CVIU), 237: 103833, 2023. (CCF-B)
On learning distribution alignment for video-based visible-infrared person re-identification
Awards
-
Doctoral Innovation Capability Enhancement Program (A-Level), Southeast University, 2025.
-
Puxin Elite scholarship, 2023.
Academic Service
-
Communication Committee Member of CAAI-ML.
-
Conference Reviewer: NeurIPS, ICLR, ICML, ICCV, AAAI, ACM MM.
-
Jounra1 Reviewer: IEEE TIP, IEEE TNNLS, IEEE TMM.