Advances in Deep Learning for Open-World Computer Vision and Pattern Recognition

Dear Colleagues,

In recent years, deep learning has significantly advanced the fields of computer vision and pattern recognition, and its applications have been widely integrated into various aspects of daily life and industrial production. While encouraging progress has been achieved in relatively simple or closed scenarios, performance in open-world environments remains unsatisfactory. Challenges stem not only from the openness of visual scenes (such as illumination variations, multi-scale objects, rainy or foggy conditions, and occlusion), but also from the openness of training and learning paradigms, including few-shot and zero-shot conditions where annotated data is scarce or unavailable. These challenges underscore the urgent need to investigate advanced deep learning techniques, encompassing diverse neural architectures (such as convolutional networks, Transformers, graph convolutional networks, and Mamba) as well as innovative learning strategies (such as few-shot or zero-shot learning), to enhance the robustness, adaptability, and generalization capability of computer vision and pattern recognition systems in open-world settings.

We are pleased to invite you to contribute to this Special Issue on “Advances in Deep Learning for Open-World Computer Vision and Pattern Recognition”. The aim of this Special Issue is to bring together cutting-edge research efforts that leverage the latest advances in deep learning to tackle open-world challenges in computer vision and pattern recognition.

This Special Issue seeks to provide a platform for researchers and practitioners to share original contributions, novel methodologies, and comprehensive reviews that address both theoretical and practical aspects. Submissions exploring innovative learning paradigms, robust model architectures, and application-driven solutions are highly encouraged.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

• Multimodal computer vision and pattern recognition;
• Open-world image recognition and understanding (including detection, classification, and segmentation, and enhancement);
• Advanced neural network architectures for visual representation;
• Few-shot, zero-shot, and other data-efficient learning strategies;
• Generative and self-supervised methods for robust visual understanding;
• Novel benchmarks, datasets, applications, and evaluation protocols for open-world vision tasks.

We look forward to receiving your valuable contributions.

Dr. Mingzhu Xu
Prof. Dr. Bing Liu
Dr. Lina Gao
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-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.

• deep learning
• open-world computer vision
• pattern recognition
• multimodal learning
• neural network architectures
• few-shot learning
• zero-shot learning
• self-supervised learning
• generative models
• benchmarks and evaluation protocols