About
I am an undergraduate student in the Information Security and Law dual-degree program at Nankai University. I conduct research with Prof. Yu Zhou in the InTime Lab at the College of Computer Science.
My work focuses on scene text understanding and visual generation, including scene text tracking, video text editing, and scene text image super-resolution. I am also interested in unified multimodal understanding and generation.
I enjoy taking ideas through the full research cycle—from literature review and model implementation to systematic experiments and academic writing—and hope to build research that has real impact.
Selected Publications
View All →Beyond Detection: A Structure-Aware Framework for Scene Text Tracking
Chenmin Yu, Liu Yu, Daiqing Wu, Gengluo Li, Zeyu Chen, Yu Zhou†
Proceedings of the 43rd International Conference on Machine Learning (ICML)
A detection-free, structure-aware framework and benchmark for scene text tracking. Sole first-author paper accepted at ICML 2026.
Structure Leads, Semantics Assist: Hallucination-Resistant Diffusion for Scene Text Image Super-Resolution
Zeyu Chen, Chenmin Yu, Fangmin Zhao, Yichao Liu, Yu Zhou†
Proceedings of the 34th ACM International Conference on Multimedia (ACM MM)
A hallucination-resistant diffusion framework for scene text image super-resolution. Second-author paper accepted at ACM Multimedia 2026.
News
Our work on scene text image super-resolution was accepted by ACM Multimedia 2026 🎉
Our work on scene text tracking was accepted by ICML 2026 🎉
Our invention patent for scene text tracking was granted in China