About
I am a Master student at the School of Artificial Intelligence and Data Science, University of Science and Technology of China, advised by Prof. Fuli Feng and Prof. Fengbin Zhu(NUS). Prior to this, I obtained a BSc degree from the Zhejiang Gongshang University, advised by Prof. Hua Zhang.
My research interests center on Multimodal Understanding. I have progressively expanded my focus from foundational text and static image-text processing to my current primary area: dynamic video understanding.
Selected Publications
View All →MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval
Fengbin Zhu, Zijing Cai, Yuzhe Wang, Pengyang Shao, Wenjie Wang, Fuli Feng, Richang Hong, Tat-Seng Chua
arXiv preprint arXiv:2603.13349
Multi-schema prompting powered token-feature woven attention network for short text classification
Zijing Cai, Hua Zhang, Peiqian Zhan, Xiaohui Jia, Yongjian Yan, Xiawen Song, Bo Xie
Pattern Recognition
Education
University of Science and Technology of China
M.Eng. in Electronic and Information Engineering
Sept. 2025 - June. 2028
Zhejiang Gongshang University
B.Sc. in Software Engineering
Sept. 2020 - June. 2024
News
Our paper MURE has been released on arXiv 📄
Starting my first internship at ByteDance for algorithm research 🧑🏻💻
Starting my M.Eng. at the University of Science and Technology of China 🇨🇳
Our work MP-TFWA has been accepted by PR 2024 🎉