Special Issue "Multimedia and Cross-modal Retrieval"
A special issue of Technologies (ISSN 2227-7080).
Deadline for manuscript submissions: 31 December 2018
Prof. Dr. Ralph Ewerth
Dr. Anett Hoppe
Leibniz Information Centre for Science and Technology, Technische Informationsbibliothek (TIB), Welfengarten 1 B, 30167 Hannover, Germany
Website | E-Mail
Interests: search as learning; multimedia retrieval; semantic web technologies; user profiling; science reproducibility; visual analytics; computer ethics
The proliferation and importance of multimedia data have increased significantly in recent years. This is obvious for the World Wide Web (social media data, videos, etc.), but, also, automatically-generated sensor data have become more and more relevant. In the era of big data, automatic indexing and understanding of multimedia information are essential to enable semantic content-based searches. Advanced analytics and intelligent human–computer interaction technologies are crucial to enable the exploration of large multimedia and multimodal datasets. Finally, there is a call for more transparency in (multimedia) retrieval systems—applications ranging from detection and adaptation of biased machine learning models to automatic identification of fake information.
In this Special Issue we seek for contributions in the field of multimedia/multimodal analysis and retrieval in a broad sense. We invite submissions from, but not limited to, the following subject areas:
(a) analysis and understanding of multimodal data and cross-modal searches;
(b) social media analysis;
(c) affective multimedia content analysis;
(d) multimedia analytics, machine learning and deep learning for multimedia;
(e) HCI and visualisation for exploration of large multimedia databases
(f) multimedia applications for academic search, digital humanities, sports, medicine, etc.
If you are not sure if your paper fits the focus of this Special Issue, please contact the Guest Editor.
Prof. Dr. Ralph Ewerth
Dr. Anett Hoppe
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 papers will be 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. Technologies is an international peer-reviewed open access quarterly 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 350 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.
- Content-based multimedia analysis and retrieval
- Analysis and understanding of multimodal data
- Cross-modal search and retrieval
- Social media analysis and search
- Affective multimedia content analysis
- Transparency and bias of multimedia retrieval results
- Novel interfaces and HCI for multimedia data
- Machine learning and deep learning for multimedia
- Multimedia information representation and knowledge graphs
- Multimedia browsing, summarisation, and visualisation
- Multimedia analytics
- Applications: academic (multimedia) search engines, digital humanities, sports, medicine
The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.
Author: Michael Riegler
Abstract: We are witnessing the emergence of a myriad of systems for quantification of sport and physical activity. These are frequently touted as game changers and may be a key for future sports development. The vast amount of collected data is often displayed in fancy graphs. However, the analysis behind that data is usually done manual. Apart from that retrieving information in such systems can also be a tedious task.
In this respect, machine learning has the potential in becoming an important tool in assisting sport professionals in their tasks. This is not just important to improve the team performance, but also for example to protect players from injuries or to retrieve information from the past.
In this paper, we present an extended version of PMSys, a player monitoring system, where we try to predict future positive and negative peaks in an athlete's performance. Using the short-term memory network deep learning method, we analyze subjective data from to Norwegian soccer teams, and our system is capable to predict peaks in most scenarios with an precision and recall of at least 90% or higher.