Deep Learning for Multimedia Processing

Dear Colleagues,

Deep learning (DL) technologies have become one of the core technologies in artificial intelligence for multimedia data analysis. In recent years, DL has been successfully explored in various multimedia applications such as natural language processing, visual data analytics, speech recognition, etc. DL inspired from the neuroscience field, building neural networks (NN) structured in a way that resembles the human brain. Considering multimedia data are characterized as large, unstructured, and heterogeneous, DL has the potential to overcome these issues by allowing computers to easily and automatically extract features from unstructured data without the need to rely on human intervention. The convergence of big annotated data and affordable CPU/GPU hardware has allowed the training of neural networks for multimedia analysis. However, there are a lot of critical aspects in multimedia DL: (1) multimedia big data efficient management; (2) utilization of different data modalities exploiting DL; and (3) explainability, insight view and understanding of the DL decision-making mechanisms.

The main aim of this Special Issue is to seek high-quality submissions that highlight latest research findings, suggesting theories and practical solutions for various applications on multimedia analysis utilizing deep learning technologies.

The topics of interest include (but are not limited to):

• Deep learning for multimedia analysis;
• Deep learning algorithms and architectures for multi-modal data analysis;
• Deep learning algorithms for clustering and classification;
• Deep learning algorithms for image segmentation and data annotation;
• System and software architecture of DL-based multimedia systems;
• Multimedia applications based on DL;
• Deep learning algorithms for forecasting;
• Deep learning algorithms for quality estimation/ prediction;
• Datasets, benchmarks, and validation of deep learning models;
• Novel visualization technologies for deep learning algorithms;
• Methods for explainability of deep learning algorithms.

Prof. Dr. Vassilios Chatzis
Prof. Dr. Stelios Krinidis
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. 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
• multimedia analysis
• big data analysis
• deep learning architectures
• machine learning
• data analytics
• visual analytics