http://www.journals.elsevier.com ... in-computer-vision/
Special Issue on Binary Representation Learning in Computer Vision
Summary and Scope: In the big data era, the volume of data has been dramatically enlarged than before. The traditional representation of data or feature learning algorithms may not work well or be computationally tractable for large-scale applications, such as image retrieval, object recognition, etc. It is desirable to develop new, efficient data representation or feature learning/indexing techniques, which can be easily performed with big data and achieve promising performance in the related tasks. In most recent years, the data-dependent hashing or compact binary code learning techniques have attracted broad research interests in computer vision, due to the high efficiency of storage and pairwise comparison with the Hamming distance. Benefiting from the nature of binary codes, these methods can well help perform various vision tasks (e.g., retrieval, classification), especially the ones with large-scale data. Recently, the hashing techniques have been shown to achieve promising performance in various applications in computer vision, such as image retrieval, object recognition and classifier training. This special issue will focus on the most recent progress on binary representation learning or data-dependent hashing methods for various visual tasks with large-scale data, such as content-based image/ video classification, image retrieval/classification, image annotation, multimedia processing and visual semantic analysis. This special issue will also target on related fast feature extraction or representation learning techniques, which can well handle large-scale visual tasks. The primary objective of this special issue fosters focused attention on the latest research progress in this interesting area. The special issue seeks for original contribution of work, which addresses the challenges from the binary code learning and the related fast representation learning algorithms for large-scale data. The list of possible topics includes, but not limited to: - Novel locality sensitive hashing algorithms
- Large-scale indexing algorithms
- Learning based or data-dependent hashing/indexing methods
- Visual recognition (e.g., detection, categorization, indexing, matching, segmentation, grouping) with binary code learning or hashing techniques
- Biometrics with binary representation learning
- Binary codes learning for visual classification/detection/retrieval/tracking
- Novel applications of hashing or binary representation learning
- Deep learning techniques for binary representation learning
- Fast feature extraction methods for visual data
- Fast learning algorithms for visual representation
- Big data, large scale methods
Submission Guideline Authors should prepare their manuscript according to the Guide for Authors available from the online submission page of the Neurocomputing journal athttp://www.journals.elsevier.com/neurocomputing/. Authors should choose “SI: Binary Learning” under Article Type. All the papers will be peer-reviewed following the Neurocomputing reviewing procedures. Important Dates: - Paper submission due: Sep. 20, 2015
- First notification: Nov. 20, 2015
- Revision: Jan. 20, 2016
- Final decision: Feb. 20, 2016
- Publication date: May 1, 2016 (Tentative)
Guest Editors:
| 
发表于 2015-9-2 20:25:18