The quest to endow AI systems with powerful visual perception capabilities akin to, or even surpassing, human vision in complex environments is a technical challenge within the "Next Generation AI" technology framework. In domains such as medical precision therapy, artistic scene design, and deep-sea ecological monitoring, intelligent perception technologies still face insufficient accuracy and poor universality when confronted with complex scenes.

The field of computer vision has undergone a significant evolution, propelled by the remarkable progress in large-scale foundation models: from the perception of general or salient objects to the latest task of understanding camouflaged scenes. The vanguard of this evolution includes pioneering models aimed at addressing the complexity of camouflaged scenes, such as the Search Identification Network (SINet), and datasets like the MoCA dataset from the University of Oxford. These include models for detecting camouflaged objects in images and videos, which have enhanced the ability of visual systems to distinguish camouflaged objects from their surroundings. These advancements are not only theoretical milestones but also practical implementations that have transformed our approach to understanding camouflaged scenes.

In light of these developments, CAAI Artificial Intelligence Research is to announce a Special Issue dedicated to exploring cutting-edge research and innovations in the field of "Camouflaged Scene Understanding". This Special Issue calls for researchers to submit original articles that delve into the intricacies of camouflage detection and recognition models, elucidating their architectures, training methodologies, and showcasing their profound impact on various vision tasks, including multimodal perception, instance segmentation, object segmentation, and 3D/2D applications. We invite contributions that explore a wide range of topics, including but not limited to:

• Novel algorithms and models for detecting and segmenting camouflaged objects in complex scenes.
• Techniques for improving the robustness and accuracy of camouflage detection across different environments.
• Studies on the psychological and physiological aspects of human perception of camouflage.
• Applications of camouflaged scene understanding in healthcare, wildlife conservation, surveillance, and other domains.
• Benchmark datasets and evaluation protocols for camouflage detection and recognition.
• Other related techniques.

Editorial Team

Leading Guest Editor:
Dr. Deng-Ping Fan
Professor
Nankai International Advanced Research Institute (SHENZHEN• FUTIAN),
Nankai University,
Shenzhen, China
Email: fdp@nankai.edu.cn

Biography: Deng-Ping Fan is affiliated with the Nankai International Advanced Research Institute (SHENZHEN• FUTIAN) and serves as a full professor and the deputy director of the Media Computing Lab (MCLab), College of Computer Science, Nankai University, China. Before that, he was a postdoctoral researcher working with Prof. Luc Van Gool in Computer Vision Lab @ ETH Zurich. During 2019–2021, he was a research scientist (PI) and team lead of IIAI-CV & Med in IIAI. His research interests are in computer vision, machine learning, and medical image analysis. Specifically, he focuses on dichotomous image segmentation (general object segmentation, camouflaged object segmentation, saliency detection) and multi-modal AI. His expertise has been recognized with several accolades, including the Best Paper Finalist Award at IEEE CVPR 2019, Best Paper Award Nominee at IEEE CVPR 2020, and Best Paper at NeurIPS Workshop 2023.

Homepage: https://dengpingfan.github.io/pages/People.html

Co-Guest Editors:

Dr. Huazhu Fu
Principal Scientist
Institute of High Performance Computing,
Agency for Science, Technology and Research (A*STAR)
Singapore
Email: hzfu@ieee.org

Biography: Dr. Huazhu Fu is a Principal Scientist at the Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore. His research interests encompass medical image analysis, AI for healthcare, and trustworthy AI. He has published more than 200 papers in top conferences and journals (e.g., Nature Machine Intelligence, Nature Communications, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), and IEEE Transactions on Medical Imaging (TMI)) with over 21,000 citations on Google Scholar. He has been recognized with several awards, including the Best Paper Award at ICME 2021, the Best Paper Award at MICCAI-OMIA 2022, and the Best Paper Award at MICCAI-DeCAF 2023. He serves as an associate editor for several journals, including IEEE Transactions on Medical Imaging (TMI), IEEE Transactions on Neural Networks and Learning Systems (TNNLS), IEEE Transactions on Artificial Intelligence (TAI), and IEEE Journal of Biomedical and Health Informatics (JBHI).

Homepage: https://hzfu.github.io

Dr. Fahad Shahbaz Khan
Professor
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
Abu Dhabi, United Arab Emirates
Email: fahad.khan@liu.se

Biography: Fahad Shahbaz Khan is a professor and the deputy department chair of Computer Vision at MBZUAI. From 2012 to 2014, Khan was a postdoctoral fellow and then a research fellow (2014-2018) at Computer Vision Laboratory, Linköping University, Sweden. In 2018, he was awarded the Docent title in computer vision from Linköping University, Sweden. Prior to joining MBZUAI, Khan was a lead scientist at the Inception Institute of Artificial Intelligence (IIAI), Abu Dhabi, United Arab Emirates. Khan's research interests include a wide range of topics within computer vision, including object recognition, detection, segmentation, tracking and action recognition. Khan has achieved top ranks on various international challenges and received the best paper award in the computer vision track at IEEE ICPR 2016.

Homepage: https://mbzuai.ac.ae/study/faculty/fahad-khan/

Dr. Fuchun Sun
Professor
Department of Computer Science and Technology,
Tsinghua University
Beijing, China
Email: fcsun@tsinghua.edu.cn

Biography: Funchun Sun received the Ph.D. degree in computer science from Tsinghua University in 1997. He is a full professor with the Department of Computer Science and Technology, Tsinghua University, China. His current research interest includes robotic perception and cognition. He serves as an associate editor of a series of international journals, including IEEE Transactions on Systems, Man and Cybernetics: Systems, IEEE Transactions on Fuzzy Systems, Mechatronics, and Robotics and Autonomous Systems. He is a fellow of IEEE.

Homepage: https://www.cs.tsinghua.edu.cn/csen/info/1312/4393.htm