Hello! My name is Zeqin Yu, and I am currently a second-year PhD student at Sun Yat-sen University (Sep. 2023 - Jun. 2027), advised by Prof. Jiangqun Ni. I completed my Master’s degree at Shenzhen University, where I was advised by Prof. Bin Li and worked in the Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security. I obtained my Bachelor’s degree from Shenzhen University as well.
My research interests are primarily focused on multimedia forensics and security, particularly in detecting and preventing manipulation and forgery of images, videos, and other media content. I also have extensive experience in competitions and data creation, particularly with real-world tampered images and videos.
If you are interested in my research or would like to explore collaboration opportunities, feel free to reach out! I am also currently looking for internship or exchange student opportunities!
Experience
Alibaba Security, Jul. 2021 - Nov. 2021
- Research Intern, advised by Dr. Rui Yang and Dr. Jishen Zeng.
- Conducted research on image forensics in real-world scenarios, focusing on screenshot image forensics.
Publications
Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization
Zeqin Yu, Jiangqun Ni, Jian Zhang, Haoyi Deng, Yuzhen Lin
Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025) (Oral)
DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization
Zeqin Yu, Jiangqun Ni, Yuzhen Lin, Haoyi Deng, Bin Li
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024)
Learning to Locate the Text Forgery in Smartphone Screenshots
Zeqin Yu, Bin Li, Yuzhen Lin, Jinhua Zeng, Jishen Zeng
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023)
- The partial datasets proposed in this paper were applied to the “2022 Real-World Image Forgery Detection Challenge” (真实场景篡改图像检测挑战赛).
- Additionally, a portion of this dataset has been used in the “ICDAR 2023 DTT in Images 1: Text Manipulation Classification” and “ICDAR 2023 DTT in Images 2: Text Manipulation Detection” competitions, although the organizers have not publicly disclosed this.
- If you use the data from these competitions in your research, please cite our paper.
Research Grants
- Special Fund for the Cultivation of Science and Technology Innovation for Guangdong University Students (PI), 20kRMB, 2022.04-2024.04. (Outstanding)
Reviewer
TPAMI, ACM MM, NeurIPS
Hornors & Awards
- 1st Place Award ×2, respectively in the Detection Track and the Localization Track, ICCV 2025 Detecting Synthetic Manipulations in ID Documents (DeepID 2025), 2025. (Solution)
- 1st Place Award, Fifth China Graduate AI Innovation Competition, CPIPC, 2023.
- Outstanding Graduates, Shenzhen University, 2023, 2020.
- Tencent Innovation Scholarship, Tencent Foundation, 2023.
- 3rd Place Award, First National Electronic Data Forensics Competition, 2023.
- 2nd Place Award, First China Graduate Network Security Innovation Competition, CPIPC, 2022.
- 3rd Place Award, First AI based Channel Modeling and Generating Competition, OPPO, 2022.
- 2nd Place Award, CCF Big Data & Computing Intelligence Contest Competition, CCF-BDCI, 2021.
- Other Top 10 Awards: 4 times