Neurocomputing Special Issue LSMV 2017 : Learning System in Real-time Machine Vision (SI: Learning Vision)
Call For Papers
With the widespread use of deep learning in training computer to understand human, many researches in extracting human senses have been conducted. The deep learning technique makes a step forward to provide hidden features and end-to-end knowledge representation for many precentral issues e.g. motion and texture style etc. Such new information channels and other multisensory priors could be valuable constrains for optimization step and further boom the general performance. In the context, the rapid and precise dense correspondence approach can significantly improve the experience of the augmented reality in terms of compatibility of mixing of virtual environment and reality space.
Learning system in particular the neural system may have many applicable fields. In the real-time perception, the information observed by the dynamical behavior of the object of interest or by the motion of the camera itself is a decisive interpretation for representing natural phenomena. Many real-world problems are related to the low-level characterization of such information, for example dense correspondence estimation, which has become one of the most active fields because such characterizations can be extremely embedded into a large number of other higher-level fields and application domains. However, for many state-of-the-art approaches, although the precision has reached a reasonable level, the related applications are still limited by the low performance in runtime. In this case, the neural system provides great potentials to speed up the tedious computation of such typical vision problems e.g. patch detection, matching and constrained optimization; as well as not limited to the general applicable problems in virtual reality, augmented reality and post-production.
This special issue calls for high quality, up-to-date technology related to learning system in computer vision, as well as the related applications in augmented reality and post-production. This special issue serves as a forum for researchers all over the world to discuss their works and recent advances in this field. Both theoretical studies and state-of-the-art practical applications are welcome for submission. All submitted papers will be peer-reviewed and selected on the basis of both their quality and their relevance to the theme of this special issue. The list of possible topics includes, but not limited to:
Rapid Learning and Neural System for Computer Vision and Augmented Reality
Deep Learning for Accelerating Dense Correspondence Estimation
Deep Learning Features for Dense Motion Detection
Fast Training Scheme for Neural System
Learning based Constraint for Energy Optimization
Learning Optical Flow Estimation using Additional Sensors
Real-time Augmented Reality and The Related HCI Evaluation Approach
Dense Correspondence Estimation for Difficult Cases e.g. Non-rigid Object, Smoke
Rapid Learning and Neural System for Post-production
Manuscript Submission Deadline: January 31 2017
First round review decision: March 31 2017
Second round review decision: April 30 2017
Final Manuscript Due: Jun 30, 2017
Expected Publication Date: August 31, 2017
Authors should prepare their manuscript according to the Guide for Authors available from the online submission page of the Neurocomputing journal at http://www.journals.elsevier.com/neurocomputing/. Authors should choose "SI: Learning Vision" under Article Type. All the papers will be peer-reviewed following the Neurocomputing reviewing procedures.
Dr. Wenbin Li, Research Associate at Imperial College London, UK.
Dr. Zhihan Lv, Assistant Professor at SIAT, Chinese Academy of Science, China.
Dr. Darren Cosker, Associate Professor at CAMERA, University of Bath, UK.
Dr. Yong-liang Yang, Assistant Professor at University of Bath, UK.
Dr. Anders Hedman, Associate Professor at KTH Royal Institute of Technology, Sweden.