Special Session 12
Special Session 12: Visual Information Enhancement, Understanding and Detection in Open-World Scenarios
Description:
This special session focuses on the processing and analysis
of visual information in open-world scenarios, covering the
entire pipeline from image/video enhancement and multimodal
understanding to object detection and semantic analysis.
Open-world environments are characterized by complexity,
diversity of objects, and uncontrolled conditions, placing
higher demands on the robustness, generalization, and
real-time performance of vision systems. The session aims to
gather the latest research advances and explore how
technologies such as deep learning, generative models,
cross-modal fusion, and adaptive learning can improve the
perceptual and cognitive capabilities of vision systems in
real-world open environments. It seeks to promote
applications in fields such as intelligent surveillance,
remote sensing analysis, medical image processing and
human-computer interaction.
Session organizers
Prof. Minghua Zhao, Xian University of Technology, China
Assoc. Prof. Jing Hu, Xian University of Technology, China
Assoc. Prof. Shuangli Du, Xian University of Technology, China
Assco. Prof. Cheng Shi, Xian University of Technology, China
The topics of interest include, but are not limited
to:
• Image/Video Enhancement and Restoration (denoising,
super-resolution, deblurring, low-light enhancement, etc.)
• Object Detection, Tracking, and Recognition in Open-World
Scenarios
• Cross-Modal Visual Understanding (vision-language models,
multi-sensor fusion)
• Domain Adaptation, Zero-Shot/Few-Shot Learning for Vision
Tasks
• Scene Understanding and Semantic Segmentation in Open
Worlds
• Visual Generative Models for Data Augmentation and
Synthesis
• Robust, Interpretable, and Secure Vision Systems
• Real-Time Visual Computing and Edge Intelligence
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 12
(Visual Information Enhancement, Understanding and Detection in Open-World Scenarios)
Template Download
Introduction of session organizers
Prof. Minghua Zhao
Xian University of Technology, China
Minghua Zhao, received the Ph.D. degree from Sichuan University, Chengdu, China, in 2006. She is currently a professor with the School of Computer Science and Engineering, Xian University of Technology, Xian, China. Her research interests include digital image processing, pattern recognition, computer graphics, and computer vision.
Assoc. Prof. Jing Hu
Xian University of Technology, China
Jing Hu, received her Ph.D. degree in Communication and Information Systems from Xidian University, Xi’An, China, in 2018. She is currently an Associate Professor at the School of Computer Science and Engineering, Xi’an University of Technology, Xi’an, China. Her research interests include hyperspectral image super-resolution and anomaly detection.
Assoc. Prof. Shuangli Du
Xian University of Technology, China
Shuangli Du received the Ph.D. degrees in computer science from Sichuan University in 2017. She is currently an Associate Professor at the School of Computer Science and Engineering, Xi’an University of Technology, Xi’an, China. In 2014, she was a Visiting Student with the Agency for Science, Technology and Research (A*STAR), Singapore. Her research interests include low-rank decomposition, computer vision, and pattern recognition.
Assco. Prof. Cheng Shi
Xian University of Technology, China
Cheng Shi received the B.S. degree from Xian University of Architecture and Technology, Shanxi, China, in 2009, the M.S. and ph.D. degrees from Xidian University, Shanxi, China, in 2012 and 2016, respectively, and worked as the postdoctoral research fellow with University of Macau, China, from 2016 to 2018.
She is currently working as an Associate Professor with the School of Computer Science and Engineering, Xian University of Technology, China. She is the author or coauthor of more than 20 publications on image processing, including international journal papers, conference papers, and book chapters. She has also been a reviewer of several journals, such as IEEE TGRS, IEEE JSTARS, IEEE TNNLS, and MTAPs. Her research interests include deep learning, image processing, and pattern recognition.