Cross Modality Deep Learning and Knowledge Representation

Dear Colleagues,

Over the last decade, the amounts of different types of media data, such as texts, images and videos, have rapidly increased on the Internet. It is common for different types of data to be used to describe the same events or topics. These different types of data are referred to as multi-modal data, which exhibit heterogeneous properties. Many studies have applied deep learning techniques for multi-modal data. Deep learning techniques often require a huge volume of data, from which hidden knowledge can be extracted. The challenge is that, although most deep learning approaches have excellent performance, the result might not be understandable by humans and thus might be difficult to apply in practice. Therefore, we also focus on the construction of knowledge and representation of network models in the research process.

Cross modality deep learning and knowledge representation refers to any kind of learning that involves information obtained from more than one modality, aiming to bring together quantitative, innovative research that focuses on modeling knowledge through deep learning networks on multi-modal data to reveal the inner regularity and representation level of multi-modal knowledge representation.

In this Special Issue, authors are invited to submit manuscripts on any topic of cross modality deep learning, knowledge representation, and related applications. Contributions and perspectives of new emerging techniques are of particular interest. We also welcome studies showing recent technical progresses, new applications and related research. Potential topics include but are not limited to the following:

• Deep learning, supervised learning and un-supervised learning for cross-modal data
• Deep feature representation for cross-modal data
• Cross-modal semantic understanding via deep learning
• Multi-modal data embedding and feature fusion
• Large-scale cross modal data indexing and fast search
• Deep-learning-based cross modal hashing
• Semantic similarity learning for cross-modal data
• Semantic based cross-modal data retrieval
• Interactive query for cross-modal data
• Spatial-temporal cross-modal data analysis and mining
• Scene understanding, event detection, object detection and tracking via deep learning
• Information extraction
• Knowledge graph
• Semantic network
• Named entity recognition
• Relation extraction
• Event extraction
• Natural language processing

Prof. Dr. Shichao Zhang
Dr. Jinjing Shi
Dr. Chengyuan Zhang
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. Big Data and Cognitive Computing is an international peer-reviewed open access monthly 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 1800 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.