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 analysis and synthesis
    Mathematical morphology
    Computer vision
    Image understanding and scene analysis
    Video understanding
    RGB-D and 3D processing
    Deep learning for visual signal processing
    Deterministic and stochastic image modeling
    Visual data reduction and compression
    Image coding and video communication
    Virtual and augmented reality for visual communication
    Privacy-Enhancing technologies for images and videos
    Data hiding, perceptual hashing, fingerprinting for images and videos
    Image and video forensics and counterforensics
    Biological and medical imaging
    Early processing in biological visual systems
    Psychophysical analysis of visual perception
    Remote sensing

Special Issue on Generative Media Processing, Computing, and Evaluation
Día de Entrega: 2025-03-01

In the new era of AI-Generated Content (AIGC), the production, processing, and presentation of visual content are being revolutionized. Especially, the rise of large language/vision models has thrust Generative AI into the spotlight. The way of multimedia processing has been dramatically changed to generative-like manners. Generative Media Processing, Computing, and Evaluation leverage the emerging generative AI and allow to create and process multimedia, understand content by media computing, and analyze challenges by comprehensive evaluation. Research communities are also seeking further advancements of media by multi- and cross-modalities, e.g., taking text modality as prompt to create or understand video. The issue aims to highlight the latest advancements and breakthroughs in related cutting-edge techniques, methods, applications, and theoretical developments that are shaping the future of generative media, fostering innovation in creating, enhancing, and interpreting media data.

Full scope of the Special Issue:

    Generative models for media generation, acquisition, compression, and processing, e.g., VAE, GAN, Transformer, NeRF, Gaussian Splatting, Diffusion models, LLMs, etc.;
    The novel applications of classical multimedia signal processing in generative media computing for enhancing interpretability, e.g., Fourier, Wavelet, Cosine Transforms, etc;
    Novel visual computing and processing techniques for complexity reduction and quality enhancement in detection, restoration, and understanding, etc;
    Integration and synthesis of visual data with other modalities, e.g., audio, text;
    Multi- and cross-modal large vision/language models for enhancing computing and understanding, e.g., ViT, Clip, Llama, GPT4, Flan-T5, LLaVA, etc., and applications, e.g., image captioning, and HOI, etc;
    Cross-domain adaptation and transfer learning using generative models for resource efficiency;
    Novel model evaluation, benchmarking, and analysis using synthetic and realistic media data.

Guest editors:

Kejun Wu, PhD
Huazhong University of Science and Technology, Wuhan, China. 
Email: kjwu@hust.edu.cn

Lijuan Wang, PhD
Microsoft, Redmond, Washington, United States of America.
Email: lijuanw@microsoft.com

You Yang, PhD
Huazhong University of Science and Technology, Wuhan, China.
Email: yangyou@hust.edu.cn

Xinchao Wang, PhD
National University of Singapore, Singapore, Singapore.
Email: xinchao@nus.edu.sg

Gang Yu, PhD
StepFun, Shanghai, China
Email: iskicy@gmail.com

Junsong Yuan, PhD
University at Buffalo, State University of New York, Buffalo, New York, United States of America.
Email: jsyuan@buffalo.edu

Manuscript submission information:

The YJVCI's submission system (Editorial Manager®) will be open for submissions to our Special Issue from July 26th, 2024.Please refer to the Guide for Authors to prepare your manuscript and select the article type of “VSI: Generative Media” when submitting your manuscript online. Both the Guide for Authors and the submission portal could be found on the Journal Homepage: Journal of Visual Communication and Image Representation | ScienceDirect.com by Elsevier

Timeline:

Submission Open Date *26/07/2024
Final Manuscript Submission Deadline *01/03/2025
Editorial Acceptance Deadline *01/07/2025

Keywords:

(Generative Media), (AIGC), (Generative AI), (Multi-modal large models), (LLM)