Summary and Scope
With the fast development of digital imaging techniques, computing technology, and the Internet, the last decade has witnessed an exponential growth of visual information and an unprecedentedly broad range of applications of image and video. The recent advent of mobile computing platforms makes this situation more pronounced, and visual information has now become an integral part of our daily life. In order to efficiently access, utilize, and transmit visual information, image and video representation and analysis have attracted intensive attention and become one of the most active research topics in the fields of signal processing, computer vision, and artificial intelligence (AI).
Visual information analysis critically depends on effective and robust visual representations. Although many excellent visual representation schemes have been developed in the literature, they are generally designed in a manual or empirical manner. Recently, deep learning has advanced as an AI approach that can automatically discover good representations and model high-level abstractions from data. Integrating the advances in computational power and the availability of large-scale visual data, deep learning has achieved record-breaking performance on a spectrum of visual analysis tasks, including object recognition, action recognition, video summarization, event analysis, visual quality assessment, just to name a few. At the same time, the full potential of deep learning for visual representation and analysis has yet to be explored and many theoretical and practical issues in this process remain unsolved. This special issue calls for new research explorations that employ, improve, and design deep learning algorithms for visual representation and analysis. The topics of this special issue include, but are not limited to, the following:
Applications of deep learning in image and video representation and analysis, including recognition, understanding, detection, segmentation, retrieval, restoration, super-resolution, and compression;
Deep learning algorithms for RGB-D and 3D visual data representation and analysis;
Deep learning algorithms and models designed for image and video analysis, including both supervised methods like deep convolution networks and unsupervised ones like stacked auto-encoders and deep Boltzmann machines;
Deep learning algorithms that efficiently handle large-scale visual data;
Deep learning software and hardware architectures for image and video applications;
Methods to integrate past research experience on visual representation and analysis with deep learning methods.
Original papers to report the latest advances on the relevant topics are invited to be submitted through Elsevier Editorial System (EES) http://ees.elsevier.com/image/ by selecting “SI: Deep Learning with AVRA” as the article type. All the papers will be peer-reviewed following the journal reviewing procedures. All the accepted papers should be prepared according to the guidelines set out by the journal.
Paper submission due: September 15, 2015
First-round acceptance notification: December 15, 2015
Revision due: February 1, 2016
Final decision: March 15, 2016
Publication date: Summer 2016 (Tentative)
Lei Wang University of Wollongong, Australia (email@example.com)
Ce Zhu University of Electronic Science and Technology of China, China (firstname.lastname@example.org)
Jieping Ye University of Michigan, Ann Arbor, USA (email@example.com)
Jürgen Gall University of Bonn, Germany (firstname.lastname@example.org)