Special Session 9

Special Session 9: Knowledge Mining and Transfer of Multimodal Large Models for Visual Perception

Description: Focusing on the reuse and adaptation technologies of visual knowledge acquired by multimodal large models across different tasks, scenarios, and data distributions. This research transfers the knowledge pre-trained on general scenarios to specific domains such as medical image analysis, autonomous driving perception, and industrial defect detection, or realizes cross-modal transfer, so as to address the problems of data scarcity in niche scenarios and insufficient generalization ability of models.

Session organizers
Assoc. Prof. Yifan Zuo, Jiangxi University of Finance and Economics, China
Prof. Deyang Liu, Anqing Normal University, China
Lecture Jiebin Yan, Jiangxi University of Finance and Economics, China
Lecture Sanqian Li, Jiangxi University of Finance and Economics, China

The topics of interest include, but are not limited to:
• Cross-modal Feature Alignment
• Few-shot/Zero-shot Visual Processing
• Medical Image Analysis
• 3D Perception in Autonomous Driving Scenarios
• Multimodal Visual Knowledge Distillation and Parameter-Efficient Fine-Tuning
• Visual Tasks Guided by Textual Knowledge
• Adaptive Transfer of Visual Knowledge in Dynamic and Open Scenarios
• AIGC Content and Model Evaluation

Submission method
Submit your Full Paper (no less than 8 pages) or your paper abstract-without publication (200-400 words) via Online Submission System, then choose Special Session 9 (Knowledge Mining and Transfer of Multimodal Large Models for Visual Perception)
Template Download

Introduction of session organizers

Assoc. Prof. Yifan Zuo
Jiangxi University of Finance and Economics, China

Yifan Zuo, received the Ph.D. degree from the University of Technology Sydney, Ultimo, NSW, Australia, in 2018. He is currently an Associate Professor with the School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics. His research interests include Image/Point Cloud Processing. The corresponding papers have been published in major international journals such as International Journal of Computer Vision, IEEE Transactions on Image Processing, IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on Multimedia, and top conferences such as SIGGRAPH, CVPR, ICCV, AAAI.

Prof. Deyang Liu
Anqing Normal University, China

Deyang Liu is a full professor at Anqing Normal University, a visiting scholar at the University of Technology Sydney, and a specially-appointed researcher at the Advanced Research Institute of the University of Science and Technology of China. He has been recognized as an Outstanding Young Scholar of Anhui Province, a Young Top Talent in Anhui Province, and a Young Taishan Scholar of Shandong Province. His research has focused on light field imaging technology, addressing challenges such as "poor visibility, transmission inefficiency, and difficulty in measurement" in complex visual scenes. He authored more than 60 papers at highly refereed conferences and journals, as well as 19 authorized invention patents. He is a recipient of the Second Prize for Science and Technology Progress from the China Society of Image and Graphics, the Second Prize for Technological Innovation from the China General Chamber of Commerce, and the Second Prize for Natural Science from the Anhui Computer Federation (ACF).

Lecture Jiebin Yan
Jiangxi University of Finance and Economics, China

Jiebin Yan received the Ph.D. degree from the Jiangxi University of Finance and Economics, Nanchang, China. He was a Computer Vision Engineer with MTlab, Meitu. Inc, and Research Intern with MOKU Laboratory, Alibaba Group. From 2021 to 2022, he was a visiting Ph.D. student with the Department of Electrical and Computer Engineering, University of Waterloo, Canada. From 2024 to 2025, he was a postdoc with Department of Computer Science, City University of Hong Kong, Hongkong, China. He is currently a Lecturer with the School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics. His research interests include visual quality assessment and computer vision.

Lecture Sanqian Li
Jiangxi University of Finance and Economics, China

Sanqian Li, received the Ph. D degree in the Department of Computer Science and Engineering, Southern University of Science and Technology, China. Currently, she is a lecturer in School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics.
Her research interests include inverse problem, low-vision assistance, and medical image enhancement. The corresponding papers have been published in major international journals such as IEEE Transactions on Image Processing, IEEE Transactions on Circuits and Systems for Video Technology, IEEE Journal Biomedical Health Informatics, and top conferences such as MICCAI, ICASSP.