Deep Visual Recognition for Intelligent Systems and Applications

Dear Colleagues,

Visual recognition has become a key enabler of intelligent systems: the ability for machines to perceive, interpret, and react to complex visual information accurately and efficiently. Recent developments in deep learning, computer vision, multimodal modeling and edge intelligence have opened the actionability of visual recognition to new fields of applications in healthcare, transportation, robotics, manufacturing, smart cities, agriculture and security as well as human–computer interaction. To this end, intelligent systems are becoming ubiquitous and thus the demand for reliable, efficient, explainable, and practical visual recognition methods that work under real-world conditions is rapidly increasing.

This Special Issue welcomes high-quality research contributions on recent important development in deep visual recognition and their tendency and integration with intelligent systems and practical application. We invite submissions of original research articles, review papers, and case studies introducing new models and learning approaches for visual understanding tasks, as well as the benchmark characterization and practical deployment frameworks. Emphasis will be placed on contributions bridging methodological advances with practical applications, including topics such as data-efficiency, model compression, interpretability, domain adaptation and multimodal-fusion for visual recognition systems, and trustworthy AI.

All areas of deep visual recognition (the more traditional image classification, object detection, semantic segmentation; the newer action recognition, video understanding, scene analysis; and even some medical image analysis/fusion of vision with non-vision data types such as time series/sensors for creating features for decision support systems) are accepted. We particularly welcome studies that show intelligent system integration, real-time deployment or cross-domain applicability.

Topics of interest include, but are not limited to, the following:

• Deep learning methods for image and video recognition;
• Vision Transformers and hybrid visual architectures;
• Object detection, tracking, and scene understanding;
• Semantic, instance, and panoptic segmentation;
• Action recognition and human behavior analysis;
• Multimodal visual recognition and vision-language learning;
• Explainable and trustworthy visual recognition systems;
• Few-shot, zero-shot, and self-supervised visual learning;
• Domain adaptation and transfer learning for visual tasks;
• Lightweight and efficient models for edge and embedded systems;
• Medical, industrial, agricultural, and transportation vision applications;
• Visual recognition for robotics, autonomous systems, and smart environments. 

This Special Issue will serve as a forum for academics and practitioners to educate us on the state of the art, share practical solutions, and discuss future issues specific to deep visual recognition in intelligent systems. We especially welcome submissions that exhibit technical novelty, application impact, and potential for real-world deployment.

We look forward to your valuable contributions. 

Dr. Chin Poo Lee
Dr. Kian Ming Lim
Guest Editors

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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied System Innovation is an international peer-reviewed open access monthly 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 1600 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.

• deep visual recognition
• computer vision
• intelligent systems
• deep learning
• object detection
• semantic segmentation
• action recognition
• vision Transformer
• multimodal learning
• self-supervised learning
• explainable AI
• edge intelligence