Call for Papers

Call for Papers: 
Information Fusion Journal - 
Special Issue on Deep Learning for Information Fusion
(https://www.journals.elsevier.com/information-fusion/call-for-papers/call-for-papers-for-a-special-issue-on-deep-learning-for-inf)

Scope: 
In the last couple of years, deep learning algorithms have pushed the
boundaries for numerous problems in areas such as computer vision,
natural language processing, and audio processing. The performance of
advanced machine (deep) learning algorithms has attained the numbers
which were unexpected a decade ago. For a given problem, information
can be obtained from multiple sources and such multimodal datasets
represent information at varying abstraction levels. Combining
information from multiple sources can further boost the
performance. Recent research has also focused on multimodal deep
learning, i.e. representation learning paradigm which learns
joint/combined feature from multiple sources. In this relatively new
area, information from multiple sources are combined in a deep
learning framework. For example, combining audio and video data to
obtain joint feature representation.

This special issue focuses on sharing recent advances in algorithms
and applications that involve combining multiple sources of
information using deep learning. Topics appropriate for this special
issue include novel supervised, unsupervised, semi-supervised and
reinforcement algorithms, new formulations, and applications related
to deep learning and information fusion.

Important Dates: 

Submission deadline: January 1, 2018 (Extended)
First review notification to authors: April 15, 2018
Revision submission: May 30, 2018
Final review notification to authors: July 31, 2018