Hi everyone, I’m a senior undergraduate student at Xidian University, preparing to pursue my graduate studies at the University of Science and Technology of China (USTC). I have a keen interest in both server-side development and artificial intelligence algorithms. During my undergraduate years, my research primarily focused on AIGC and video understanding. In graduate school, I plan to work on research related to VLM. As of now, I’m still a rookie in the research field. If you’re interested in my work or research direction, feel free to reach out to me!
🔥 News
- 2024.06: 🎉🎉 One paper is accepted by PRCV 2024
📝 Publications
PRCV 2024
Flow-Audio-Synth:A Video-to-Audio Model which Captures Dynamic Features
YupengZheng, Zixaing Lu, Qiguang Miao, XiangzengLiu
- combining the powerful CLIP image encoder with an optical flow algorithm, focusing on both the rich static semantics and dynamic features of videos to facilitate the generation of higher fidelity, fine-grained audio
- Evaluation results show that Flow-Audio-Synth outperforms state-ofthe-art(SOTA) methods in terms of both correlation and fidelity.
🎖 Honors and Awards
- 2023.12 National Scholarship (Top 1%).
- 2023.12 Outstanding Student Model of Xidian (Top 1%).
- 2023.2 Meritorious Winner of the International College Student Mathematical Modeling Contest (Top 6%).
- 2022.11 Third place in Huawei Cloud Developer Competition Asia Pacific Division.
📖 Educations
- 2021.09 - 2025.07 (expected), Undergraduate, School of Computer Science and Technology, Xidian Univeristy, Xi’an.
- 2025.09 - 2028.07 (expected), Master’s, School of Cyber Security, University of Science and Technology of China (USTC), Hefei.
💻 Internships
- 2022.08 - 2022.12, The Hong Kong Polytechnic University, Edge Intelligence Lab, Research Assistant, Hong Kong.