MSN 2026 Workshop on 1st Edge Computing-enabled Video and Image Processing and Applications

Workshop Organizers:

Dr. Nanfeng Jiang
Xiamen University of Technology, China
Email: jnfrock@gmail.com

Prof. Tiesong Zhao
Fuzhou University, China
Email: t.zhao@fzu.edu.c

Dr. Shunzhou Wang
Henan University, China
Email: shunzhouwang@henu.edu.cn

Dr. Chao Zeng
Hubei University, China
Email: chao.zeng@hubu.edu.cn

Dr. Yingying Wang
Huaqiao University, China
Email: wyy2269@gmail.com

Short Biography of Organizers:

Dr. Nanfeng Jiang (Member, IEEE) received the Ph.D. degree in communication and information systems from Fuzhou University, Fuzhou, China, in 2023. He is currently an associate professor with the School of Computer and Information Engineering, Fujian Key Laboratory of Pattern Recognition and Image Understanding, Xiamen University of Technology, Xiamen, China. His current research interests include image/video enhancement and document image processing. He also severs as the Area Chairs of IJCNN 24~26.

 

Dr. Shunzhou Wang (Member, IEEE) is a Lecturer in the HENU-100 Talents Program at the School of Artificial Intelligence, Henan University, Zhengzhou, China. He received his Ph.D. degree in Computer Science and Technology from Beijing Institute of Technology in 2023, and was a postdoctoral researcher at Peking University Shenzhen Graduate School from 2023 to 2025. His research interests include multimedia information processing and computer vision, with a current focus on light field image super-resolution, remote sensing image super-resolution, 3D Gaussian splatting, depth estimation, and industrial anomaly detection. Dr. Wang has published 50+ papers in CCF-recommended journals and conferences, including IEEE TIP, IEEE TMM, IEEE TGRS, and AAAI. His work includes one ESI highly cited paper; Google Scholar reports 1,500+ citations and an h-index of 18. He has led several provincial or ministerial-level research projects and won 1st Place and 2nd Place in the NTIRE 2024 Light Field Image Super-Resolution Challenge at the CVPR 2024 Workshop.

 

Dr. Chao Zeng received the B.Eng. degree from Hubei University in 2015, MSc. degree from Sichuan University in 2018, and PhD degree from the City University of Hong Kong in 2023. He is currently a lecturer in the School of Artificial Intelligence, Hubei University. His primary research interests fall in the fields of Machine Learning, Computer Vision, and Natural Language Processing.

 

Prof. Yingying Wang received the B.E. degree from Shandong University, Jinan, China, in 2016, and the M.S. degree from Nanyang Technological University, Singapore, in 2017. After graduation, she worked as a Senior Engineer at Infineon Technologies, Singapore, from 2017 to 2022. She received the Ph.D. degree in Computer Science and Technology from the Institute of Artificial Intelligence, Xiamen University, Xiamen, China, in 2026. She is currently a Full Professor with the College of Computer Science and Technology, Huaqiao University, Xiamen, China. Her current research interests include remote sensing image processing, image fusion, and quantitative reconstruction in medical MRI.

 

Prof. Tiesong Zhao (Senior Member, IEEE) received a Bachelor's degree in Electrical Information Engineering from the University of Science and Technology of China in 2016 and a Ph.D. in Computer Science from the City University of Hong Kong in 2012. He is currently a Minjiang Distinguished Professor with the College of Physics and Information Engineering, Fuzhou University, Fuzhou, China. His research interests include visual-haptics analytics, coding, quality assessment, transmission, display and their applications in embodied AI. He has been an Associate Editor for IEEE Transactions on Image Processing (2024-now), a Senior Area Editor for IEEE Signal Processing Letters (2025-now) and an Editor/Executive Editor for CSIG Communications (2022-now)

 

A Brief Description of Workshop:

       Recent advances in artificial intelligence, computer vision, mobile computing, and intelligent sensing have significantly promoted the development of video and image processing technologies. Meanwhile, the rapid growth of edge computing provides a new computational paradigm for deploying visual intelligence closer to data sources, such as cameras, mobile devices, embedded systems, unmanned platforms, industrial sensors, and Internet-of-Things terminals. Compared with traditional cloud-based visual processing, edge computing enables lower latency, reduced bandwidth consumption, better privacy protection, and stronger real-time responsiveness, which are essential for many emergingapplications. However, video and image processing under edge computing environments still faces several fundamental challenges. First, visual data are usually high-dimensional, redundant, andcomputationally expensive to process, while edge devices are often constrained by limited computation, storage, memory, and energy resources. Second, real-world visual scenarios are highly dynamic and complex. Images and videos captured by edge devices may suffer from noise, blur, compression artifacts, low illumination, adverse weather, occlusion, camera motion, and unstable transmission conditions. Third, many vision applications require real-time or near-real-time responses, such as intelligent transportation, smart surveillance, autonomous navigation, industrial inspection, medical assistance, remote sensing, mobile robotics, and augmented reality. These requirements make it necessary to jointly consider visual quality, task accuracy, model complexity, communication cost, and deployment efficiency.

       The proposed workshop aims to provide a focused forum for researchers, engineers, and practitioners working on edge computing-enabled video and image processing. It will bring together communities from edge computing, computer vision, multimedia, signal processing, mobile sensing, embedded AI, and real-world applications. The workshop will encourage discussions on both algorithmic innovation and system-level deployment, including lightweight image/video restoration, efficient visual recognition, edge-cloud collaborative processing, neural network compression, adaptive visual transmission, privacy-preserving visual analytics, and application-oriented edge intelligence.

Potential Topics of Interest:

• Edge computing-enabled image and video processing
• Lightweight image and video restoration on edge devices
• Real-time video enhancement, denoising, deblurring, super-resolution, and compression artifact removal
• Efficient neural networks for edge vision systems
• Model compression, pruning, quantization, distillation, and neural architecture search for visual processing
• Edge-cloud collaborative video/image analysis
• Adaptive visual sensing, transmission, and processing
• Task-oriented image and video enhancement for downstream vision applications
• Privacy-preserving visual analytics at the edge
• Federated learning and distributed learning for edge visual intelligence
• Resource-aware image/video understanding and recognition
• Low-power visual perception for mobile, embedded, and IoT devices
• Video analytics for smart cities, intelligent transportation, industrial inspection, healthcare, remote sensing, robotics, and autonomous systems
• Benchmark datasets, evaluation protocols, and deployment platforms for edge visual processing

Paper Submission Guidelines:

       All submissions should follow the IEEE 8.5″x 11″Two-Column Format. Each submission can have up to 6 pages. Authors of accepted papers are expected to present their papers at the workshop. All submissions to MSN 2026 must be uploaded to EasyChair: https://easychair.org/conferences/?conf=msn2026

Important Dates:

• Sep. 20, 2026

  Paper Submission

• Oct. 30, 2026

  Author Notification

• Nov. 7, 2024

  Camera-ready

• Dec. 18-20, 2024

  Conference Date