This Special Session aims to bring together researchers and practitioners from computer vision, pattern recognition, deep learning, multi-modal intelligence and related engineering fields. It intends to bridge fundamental theoretical advances of visual computing with diverse real-world deployment demands. We welcome original contributions covering theories, algorithms, network architectures, datasets, embedded systems and practical implementations for visual intelligence. This session encourages cross-domain studies, including but not limited to safety monitoring, intelligent transportation, industrial inspection, healthcare informatics, smart city and other complex real-world scenarios. We invite high-quality submissions reporting innovative research works, open datasets, system prototypes, as well as comprehensive review articles. Areas to be covered in this Research Topic may include, but are not limited to:

• Object detection, recognition and instance understanding in complex and dynamic scenes;
• Video object tracking, motion estimation and spatial-temporal visual analysis;
• Human/object behavioral analysis, pattern mining and anomaly detection;
• Image and video restoration, enhancement, quality assessment and feature representation learning;
• 2D/3D vision, multi-view perception and multi-modal data fusion for visual intelligence;
• Foundation models, large vision models and efficient deep learning for visual tasks;
• Lightweight model compression, edge-side visual computing and real-time vision systems;
• Visual-language understanding, visual reasoning and cross-modal generation;
• Visual datasets construction, data augmentation and domain adaptation / generalization;
• Industrial vision inspection, intelligent transportation, public safety and healthcare-oriented visual applications;
• Smart city, robot perception and other scenario-driven visual intelligence practices, etc.

The manuscript should be submitted via the submission link (http://www.easychair.org/conferences/?conf=icsip2027), or to  icsip2016@vip.163.com before the submission deadline (February 5, 2027).

Special Session Chairs:

Hongbin Liu, Shandong Jianzhu University, China

Hongbin Liu received Ph.D. degree in Control Science and Engineering from Shandong University, China, in 2019. Now he is a lecturer at the School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan, China. He is a member of the China Society of Image and Graphics, the Chinese Association of Automation, a core member of the Shandong Electronic Society and the Shandong Key Laboratory of Smart Buildings and Energy Efficiency. His current interests include multiple targets detection, tracking and behavior analysis technologies in Intelligent video surveillance scenario. He has authored/co-authored over 20 journal/conference papers. He has also served as a reviewer for many international journals/conferences in the field of image processing and pattern recognition, such as IEEE TMM, Signal Processing, SIVP, ICSIP, CCDC, etc. He won the second prize of the 2023 China Automation Association Science and Technology Progress Award.

Chunsheng Liu, Shandong University, China

Chunsheng Liu is currently an Associate Professor of Shandong University, China. He received the Ph.D. degree in Control Science and Engineering from Shandong University, China, in 2016. He was a postdoctoral fellow at the University of Washington (USA). His current research interests are automation, artificial intelligence, autonomous driving, intelligent transportation systems, and information science. He has received multiple awards including Shandong Provincial Excellent Young Scholar, Shandong Provincial Outstanding Doctoral Dissertation Award, and First Prize of Shandong Provincial Teaching Achievement Award. He has led/co-led research projects funded by the National Natural Science Foundation of China (two projects), Ministry of Science and Technology’s Key R&D Program (sub-project), Shandong Provincial Key R&D Program, and other provincial-level initiatives. He has published more than 70 SCIE-indexed scientific articles (over 20 in IEEE transactions and top-tier journals). He has achieved over 20 authorized invention patents.

Youmei Zhang, Qilu University of Technolog, China

Youmei Zhang received Ph.D. degree in Pattern Recognition and Intelligent Systems from Shandong University, China, in 2019. Now she is an associate professor at the School of Mathematics and Statistics,, Qilu University of Technology, Jinan, China. She is a member of the Chinese Society for Artificial Intelligence, the Chinese Association of Automation, a core member of the Shandong Provincial Key Laboratory of Unmanned System Intelligent Technology and Equipment. Her current interests include  marine targets detection, tracking and 3D skeleton based behavior analysis technologies in Intelligent video surveillance scenario. She has authored/co-authored over 20 journal/conference papers and has also served as a reviewer for many international journals/conferences in the field of image processing and pattern recognition, such as IEEE TIP,  IEEE TCSVT, Pattern Recognition Letters, etc. She won the second prize of the second prize of Shandong Natural Science Award in 2021 and the 2023 China Automation Association Science and Technology Progress Award.