Advanced Methods and Geometric Approaches for Computer Vision and Pattern Recognition

Dear Colleagues,

Over the past two decades, computer vision and pattern recognition have witnessed significant advancements, driven both by the rise of machine and deep learning architectures and the resurgence of geometric aware and manifold-based methods. These two paradigms—data-driven and geometry-driven—offer distinct yet complementary strengths for modeling complex visual data.

Besides the popular methods of machine and deep learning, geometric approaches aims to unravel the intrinsic, often low-dimensional, structure underlying high-dimensional data, providing elegant tools for several computer vision and pattern recognition tasks. At the same time, deep learning has delivered remarkable practical success across nearly every vision task. Geometric approaches have been the subject of intensive study over the past two decades in the fields of computer vision and machine learning. A key motivation of this Special Issue is to explore how insights from geometry and/or contermporary learning can enhance deep representations. With the rise of contemporary computer vision and deep learning, a pressing question emerges: Can data-driven learning benefit from the theoretical insights offered by manifold learning?

This Special Issue encourages contributions that explore the intersection of these paradigms and examine how classical manifold learning and geometry-based methods can enrich modern deep architectures, and vice versa. Several recent works have demonstrated the advantage of such geometrically aware models in tasks like fine-grained recognition, action recognition, medical and neuro-imaging, video analysis, etc.

This Special Issue aims to bring together original research, comprehensive surveys, and novel perspectives on contemporary or geometry-driven methodologies for computer vision and pattern recognition. The objective of this Special Issue is to promote dialog between the geometric computing community and mainstream computer vision researchers, fostering a deeper understanding of data representations and advancing robust solutions to practical visual recognition challenges.

We welcome original research, comprehensive surveys, and visionary perspectives on the theoretical developments, algorithm design, and practical applications of both manifolds and/or linear spaces.

Relevant topics include, but not limited to, the following:

• Theoretical aspects and computational methods for computer vision and pattern recognition in curved spaces.
• Riemannian optimization methods and algorithms on matrix manifolds.
• Riemannian geometry and its applications for computer vision and pattern recognition.
• Domain adaptation.
• Neuroimaging and medical image analysis.
• Computational forensics.
• Image set recognition.

Dr. Elias N. Zois
Prof. Dr. Alex Alexandridis
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 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. Applied Sciences 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 for vision
• machine learning for vision
• pattern recognition
• geometric data-driven topologies computing
• Riemannian geometry
• Riemannian computing
• optimization methods on manifolds and/or linear spaces

• Applications of Image Processing and Pattern Recognition in Biometrics in Applied Sciences (8 articles)