The Journal of Visual Communication and Image Representation publishes papers on state-of-the-art visual communication and image representation, with emphasis on novel technologies and theoretical work in this multidisciplinary area of pure and applied research. The field of visual communication and image representation is considered in its broadest sense and covers both digital and analog aspects as well as processing and communication in biological visual systems.

Research Areas include:

• Image scanning, sampling, and tessellation
• Image representation by partial information
• Local and global schemes of image representation
• Analog and digital image processing
• Fractals and mathematical morphology
• Image understanding and scene analysis
• Deterministic and stochastic image modeling
• Visual data reduction and compression
• Image coding and video communication
• Biological and medical imaging
• Early processing in biological visual systems
• Psychophysical analysis of visual perception
• Astronomical and geophysical imaging
• Visualization of nonlinear natural phenomena
• real-time imaging

Special Issue on Long-Term Action Understanding
Submission Date: 2024-02-25

Recently, pattern recognition and computer vision have been researching hotspots in artificial intelligence with widely used deep learning methods. The research contains a wide range of applications, including image classification, video understanding, 3D vision and etc. In the area of video analysis, recent research has achieved a lot of developments, especially in action understanding. While most developments in action understanding have been made for short-term videos, which is caused by the original data organization and task settings. With the development of video capture devices and data storage/transmission devices, long-term action understanding will become an important research trend in video analysis. Recently, transformer architecture has become an important method for computer vision in complicated content understanding, which paves a promising way for long-term action understanding. While long-term action understanding is still a challenging problem that includes detection, recognition, prediction reasoning and etc. Many applications occur in the open scene that the actions last long and more than one action entangles in one period. For instance, it is useful to sequentially understand different actions and describe the relationship of actions, which is particularly important for human-robot interaction and automated processing videos. In a sense, long-term action understanding is significant for drawing the “full picture” of a long-term video, which can analyze the past and predict the future.

The long-term action understanding aims to analyze the complex content in long-term videos. This special issue is to promote research on the purpose of long-term action understanding. We aim to solicit high-quality papers, both in theory and applications. Especially, the following (but not limited to) topics are the particular interests of this special issue, including:
------------
Guest editors:

Lei Chen, PhD
University of Science and Technology Beijing, Beijing, China(Computer Vision, Video Analysis, and Action Understanding) 


Ajmal Mian, PhDThe University of West Australia, Perth, Australia(Computer Vision, Artificial Intelligence, Deep Learning, and Machine Learning)

Jiwen Lu, PhDTsinghua University, Beijing, China(Computer Vision, Pattern Recognition, and Machine Learning)

Manuscript submission information:
The YJVCI's submission system (Editorial Manager®) will be open for submissions to our Special Issue from November 25th, 2023. When submitting your manuscript please select the article type VSI: Action Understanding 2023.

Timeline:
Submission Open Date *25/11/2023
Final Manuscript Submission Deadline *25/02/2024
Editorial Acceptance Deadline *25/06/2024