Intelligent Image Processing: From Data-Driven Modeling to Cross-Modal Understanding

Dear Colleagues,

Motivated by the transformative impact of artificial intelligence, the field of image processing is undergoing a fundamental paradigm shift, moving beyond traditional handcrafted algorithms toward data-driven intelligent systems. In response, a vibrant new interdisciplinary research area has emerged, centered on concepts such as "deep visual representation," "generative models," "vision-language understanding," and "embodied vision."

By integrating theories and methodologies from computer vision, machine learning, cognitive science, and computational mathematics, this field aims to build models that not only perceive visual content but also achieve a deep, contextual, and actionable understanding of the visual world. As visual data becomes ubiquitous and multimodal interaction becomes the norm, enabling machines to process and interpret images in conjunction with other modalities (e.g., language, audio) is essential for developing next-generation intelligent systems.

This interdisciplinary research topic explores the entire pipeline of intelligent image processing, from foundational data-driven modeling techniques to advanced cross-modal reasoning. It encompasses the creation, analysis, enhancement, and semantic understanding of visual data. We seek research that effectively bridges the gap between how models learn (data-driven methodologies) and how they understand and interact (cross-modal integration).

Examples of relevant topics include, but are not limited to, novel architectures for visual representation learning (e.g., advanced transformers, diffusion models), self-supervised and few-shot learning for vision, generative models for image synthesis and editing, efficient model design for edge computing, robustness and explainability of visual models, and particularly, multimodal foundation models (e.g., vision–language models) for tasks such as visual question answering, image captioning, and embodied AI.

In this Special Issue, we aim to collect reviews, expository articles, and original research papers that address the interdisciplinary themes described above. We welcome both theoretical and empirical contributions that push the boundaries of intelligent image processing.

Dr. Bin Chen
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• vision transformers
• vision few-shot learning
• vision self-supervised learning
• vision–language models
• image generation and editing
• diffusion models
• trustworthy visual AI
• embodied vision