Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Visual Pattern Discovery and RecognitionHierarchical Sparse Coding for Visual Co-occurrence Discovery

Visual Pattern Discovery and Recognition: Hierarchical Sparse Coding for Visual Co-occurrence... [In this chapter, we investigate soft assignments instead of hard assignments used in Chap. 2 and propose a hierarchical sparse coding method to learn representative mid-level visual phrases. Given multiple types of low-level visual primitive features, we first learn their sparse codes, respectively. Then, we cast these sparse codes into mid-level visual phrases by spatial pooling in spatial space. Besides that, we also concatenate the sparse codes of multiple feature types to discover feature phrases in feature space. After that, we further learn the sparse codes for the formed visual phrases in spatial and feature spaces, which can be more representative compared with the low-level sparse codes of visual primitive features. The superior results on various tasks of visual categorization and pattern discovery validate the effectiveness of the proposed approach.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Visual Pattern Discovery and RecognitionHierarchical Sparse Coding for Visual Co-occurrence Discovery

Download PDF
15 pages

Loading next page...
 
/lp/springer-journals/visual-pattern-discovery-and-recognition-hierarchical-sparse-coding-8WMRHMihcx
Publisher
Springer Singapore
Copyright
© The Author(s) 2017. This book was advertised with a copyright holder in the name of the publisher in error, whereas the author(s) holds the copyright.
ISBN
978-981-10-4839-5
Pages
29 –44
DOI
10.1007/978-981-10-4840-1_3
Publisher site
See Chapter on Publisher Site

Abstract

[In this chapter, we investigate soft assignments instead of hard assignments used in Chap. 2 and propose a hierarchical sparse coding method to learn representative mid-level visual phrases. Given multiple types of low-level visual primitive features, we first learn their sparse codes, respectively. Then, we cast these sparse codes into mid-level visual phrases by spatial pooling in spatial space. Besides that, we also concatenate the sparse codes of multiple feature types to discover feature phrases in feature space. After that, we further learn the sparse codes for the formed visual phrases in spatial and feature spaces, which can be more representative compared with the low-level sparse codes of visual primitive features. The superior results on various tasks of visual categorization and pattern discovery validate the effectiveness of the proposed approach.]

Published: Jun 16, 2017

Keywords: Visual phrase learning; Hierarchical sparse coding; Spatial pooling; Multi-feature fusion; Back-propagation

There are no references for this article.