Min Cao | multimodal learning | Best Researcher Award

Assoc Prof Dr. Min Cao | multimodal learning | Best Researcher Award

Soochow University | China

Publication Profile

Scopus

👨‍🏫 Professional Summary

Dr. Min Cao is currently an Associate Professor at the School of Computer Science and Technology, Soochow University, where he also serves as Assistant to the Dean at the Artificial Intelligence Research Institute. He is a core contributor in the field of computer vision, particularly in multimodal learning, text-based person retrieval, and person re-identification. With over 22 published papers—including in top-tier journals (SCI Q1) and prestigious conferences such as AAAI, IJCAI, and ICCV—Dr. Cao has established himself as a leading researcher. He is the recipient of multiple research grants and holds 8 authorized invention patents. Actively involved in academic service, he is the Deputy Secretary-General of the Computer Vision Special Committee of the Shanghai Computer Society and an Executive Member of CCF Suzhou.

🎓 Education

Dr. Cao received his Ph.D. in Pattern Recognition and Intelligent Systems from the Institute of Automation, Chinese Academy of Sciences (2016–2020), under the supervision of Professor Silong Peng. Prior to that, he completed his bachelor’s degree in Electronic Information Engineering at Tianjin Polytechnic University in 2014.

đź’Ľ Professional Experience

He began his academic career as an Assistant Professor at Soochow University from March 2020 to September 2023, before being promoted to Associate Professor in October 2023. In addition, Dr. Cao was a visiting scholar at the Fraunhofer Institute for Image Data Processing in Germany from 2018 to 2019, where he conducted cutting-edge research in image analysis.

🔬 Research Interests

Dr. Cao’s research interests span across multimodal learning, text-based person search, person re-identification, graph neural networks, and cross-modal retrieval systems. His work aims to enhance retrieval performance in low-source and open-world environments.

📚 Academic Contributions

He has published 22 peer-reviewed papers, including in high-impact journals such as IEEE Transactions on Circuits and Systems for Video Technology and Pattern Recognition, and at top conferences like AAAI, IJCAI, and ACMMM. He has served as the principal investigator on multiple national and provincial-level research projects, including those funded by the National Natural Science Foundation of China. Dr. Cao also holds 8 granted patents related to image-text retrieval, anomaly detection, and multimodal learning systems.

🧑‍🏫 Teaching & Mentorship

Dr. Cao has been recognized for his commitment to teaching and student mentorship, guiding students who have received national graduate scholarships and awards for outstanding theses. In 2023, he was named Outstanding Instructor at the Global Campus Artificial Intelligence Algorithm Elite Competition.

🛠️ Technical Skills

He is proficient in machine learning and deep learning frameworks including PyTorch and TensorFlow, with strong programming skills in Python and C++. His technical toolkit also includes OpenCV, Scikit-learn, LaTeX, and tools for multimodal retrieval and graph-based learning.

🏆 Awards & Honors

His work has earned numerous accolades, including First Prize in the 2024 Suzhou Computer Society Outstanding Paper Award, Second Prize in the 2022–2023 Suzhou Natural Science Academic Paper Award, and recognition for excellence in student supervision and AI competition mentoring.

📚 Top Notes Publications

1. Efficient text-to-video retrieval via multi-modal multi-tagger derived pre-screening
  • Authors: Xu, Yingjia; Wu, Mengxia; Guo, Zixin; Ye, Mang; Laaksonen, Jorma T.

  • Journal: Visual Intelligence

  • Year: 2025

2. Diversified Data Expansion Method Using Text-Based Person Image Search
  • Authors: Wang, Jingyao; Cao, Min

  • Journal: Jisuanji Gongcheng / Computer Engineering

  • Year: 2024