Recent Progress in Visual AI: Architectures, Learning, and Applications

Dear Colleagues,

With the rapid development of artificial intelligence (AI) and computer vision, novel model architectures and multimodal representation learning have become research hotspots. These new technologies not only advance visual tasks, such as segmentation, detection, and re-identification, but also show great potential in applications like autonomous driving, robotics, and medical imaging. We are curating this Special Issue to gather and showcase the latest research achievements in the field of visual AI and to explore further directions and technological innovations.

This Special Issue aims to collect innovative and emerging research findings covering a wide range of topics, from foundational model design to multimodal representation learning and specific applications. We hope that this call for papers will promote communication and co-operation between academia and industry and further drive development in this field.

We welcome submissions on, but not limited to, the following topics:

Novel Model Architecture Design:

• Applications of CNNs/Transformers in visual tasks;
• Visual state-space models (SSMs);
• Mamba models;
• Kolmogorov–Arnold networks (KANs).

Multimodal Representation Learning

• Joint understanding and generation of multimodal data;
• Cross-modal representation and alignment;
• The CLIP model and its extensions;
• Few-shot and zero-shot learning for multimodal data.

General Vision Models

• Universal segmentation models;
• Universal detection models;
• Universal depth-estimation models.

Human-Centric Tasks

• Pose estimation;
• Human parsing;
• Human detection;
• Human segmentation;
• Person re-identification.

Scene-Centric Tasks

• Indoor and outdoor scene segmentation;
• Scene detection;
• Scene depth estimation.

3D Vision

• Point-cloud understanding;
• Multi-view processing;
• RGB-D processing;
• 3D reconstruction and generation.

Integration of Large Language Models with Vision Tasks

• Applications of large language models in vision tasks;
• Fusion and innovation in vision–language

Application Domains

• Embodied intelligence;
• Autonomous driving;
• Robotic vision;
• Remote sensing image analysis;
• Medical image analysis.

Dr. Changshuo Wang
Dr. Guang Yang
Dr. Prayag Tiwari
Dr. Gang Wang
Dr. Rui** Wang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at mdpi.longhoe.net 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 100 words) can be sent to the Editorial Office for announcement on this website.

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. Electronics 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 2400 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.

• visual AI
• pattern recognition
• transformer models
• multimodal representation learning
• 3D vision
• autonomous driving