Call for papers: Deep Learning for Emerging Big Multimedia Super-Resolution
Dr. Valerio Bellandi, Università degli Studi di Milano, Italy, firstname.lastname@example.org
Dr. Abdellah Chehri, Université du Québec à Chicoutimi, Canada, Abdellah_Chehri@uqac.ca
Dr. Salvatore Cuomo, University of Naples Federico II, Italy, email@example.com
Dr. Gwanggil Jeon (Lead Guest Editor), Incheon National University, Korea, firstname.lastname@example.org
Aims and Scopes
The main aim of the super-resolution is to restore a visually pleasing high resolution image using a low-resolution image of video sequence. The higher resolution image is composed of higher pixel density with fine and precise details as compared with the low-resolution images or video. The majority of the applications, such as video surveillance, ultra-high definition TV, low-resolution face recognition and remote sensing imaging are based on super-resolutions. Thus benefiting from the broader spectrun of these applications, the super-resolution has attracted massive hige interest form both acemedia and industry. And currently, a most active research field in todays era.
Previously, most of the reseachers focus on the Machine Learning techniques, such as supervised and unsupervised learning, Reinforcement Machine Learning, Naïve Bayes Classifier, K Means Clustering, Random Forests, and Decision Tree, etc. Using these techniques, the learning techniques are unable to provide the fine and precise results. Therefore, due to the rapid advancements in the Deep Learning, Deep Network based high resolution has shown a promising performance in certain applications. Apperently, still many loops holes are still remaining that need serious attention. These loop holes open noew topics of deep learning for super resolution images and videos, such as application includes, new objective functions, new architectures, large scale images, depth images, data acquisition, feature representation, time series analysis, knowledge understanding, and semantic modeling, various types of corruption, and new applications. There still exists a gap between extracting representations (or knowledge) from big multimedia data and practical demands.
We solicit original contributions in four categories, all of which are expected to have an emphasis on deep learning and machine learning: (1) state-of-the-art theories and novel application scenarios related to deep learning for SR for big multimedia data analytics; (2) novel time series analysis methods and applications; (3) surveys of recent progress in this area; and (4) the building of benchmark datasets. This special issue serves as a forum for researchers all over the world to discuss their works and recent advances in deep learning for emerging big multimedia super-resolution. The special issue seeks for the original contribution of works that addresses the challenges of multimedia system. Papers addressing interesting real-world applications are especially encouraged. The list of possible topics includes, but not limited to:
- Supervised deep learning methods SR
- Hybrid RGB and depth image SR with deep learning
- Deep learning for large scale SR
- Hardware and systems of deep learning for SR
- New image databases for deep learning for SR
- Acceleration of deep learning for SR
- Data Visualization patterns, query processing and analysis of big multimedia data
- Business Intelligence for deep learning for SR
- Deep learning framework for big multimedia data
- Modern technologies for deep learning for SR
- 2D/3D multimedia data understanding for deep learning for SR
- Tools and applications for medicine and healthcare data (e.g. clustering, storing, ranking, hashing, and retrieval)
- Knowledge integration of multi-modal data through transfer learning and deep neural network
Submission deadline: July 15, 2020
Reviews due (accept/reject notification): October 15, 2020
Notification of final acceptance: December 15, 2020
Papers submitted to this special issue for possible publication must be original and must not be under consideration for publication in any other journal or conference. If the submission is an extended version of a previously published workshop or conference paper, this should also be explicitly mentioned in the cover letter, as well as the published paper must be cited in the submitted journal version.
The papers must be written in English and must not exceed 30 pages (single column, double space, 12 pt font, including figures, tables, and references). Authors must follow the formatting and submission instructions of MMSJ at https://www.springer.com/530 and follow the "Submit Online" link on that page. During the submission process, please make sure you're submitting to the appropriate special issue.