A Selective Sparse Coding Model with Embedded Attention Mechanism

Qingyong Li; Zhiping Shi; Zhongzhi Shi

doi:10.4018/jcini.2007100105

10% Discount on All E-Books through IGI Global’s Online Bookstore Extended(10% discount on all e-books cannot be combined with most offers. Discount is valid on purchases made directly through IGI Global Online Bookstore (www.igi-global.com)
and may not be utilized by booksellers and distributors. Offer does not apply to e-Collections and exclusions of select titles may apply. Offer expires December 31, 2022.)Browse Titles

Special Offers
- 10% Discount on All E-Books through IGI Global’s Online Bookstore
  With the continued paper shortages and supply chain issues, we have been informed by our partners that there will be substantial delays in printing and shipping publications, especially as we approach the holiday season. To help incentive the electronic format and streamline access to the latest research, we are offering a 10% discount on all our e-books through IGI Global’s Online Bookstore. Hosted on the InfoSci^® platform, these titles feature no DRM, no additional cost for multi-user licensing, no embargo of content, full-text PDF & HTML format, and more.
  Browse Titles
- IGI Global to Convert an Additional 30 Journals to Full Gold Open Access for the 2022 Volume Year
  IGI Global is to convert an additional 30 journals to full gold open access (OA) for their 2022 volume year, which will expand their OA collection to contain 60 gold open access and one (1) platinum open access journal.
  Learn More
- All IGI Global Scholarly Journals Shift to "Digital Preferred" Format
  In response to the overwhelming demand for electronic content coupled with the mission to decrease the overall environmental impacts of print production and distribution, all IGI Global journals will shift into a digital preferred model for the 2022 volume year. Under this model, journals will become primarily available under electronic format and articles will be immediately available upon acceptance. Print subscriptions and print + electronic subscriptions will still be available, but for the print version, all articles that are published during the volume year will become available at the end of the year in a single (1) printed volume.
  Learn More
- IGI Global’s New DEI e-Book Collection
  Acquire Over 320+ E-Books on Diversity, Equity, and Inclusivity from a publisher that has been dedicated to DEI since its inception over 30 years ago. Now, benefit from a collection of all of our DEI e-Books at a 90% Discount.
  Learn More
- Offering a 5% Pre-Publication Discount on
  All Reference Books Ordered Through IGI Global’s Online Bookstore*
  To support customers with accessing the latest research, IGI Global is offering a 5% pre-publication discount on all hardcover, softcover, e-books, and hardcover + e-books titles.
  *5% discount offer is eligible on hardcover, softcover, e-books, and hardcover + e-books titles and is automatically applied directly to the shopping cart. Discount offer only valid on purchases made directly through IGI Global’s Online Bookstore and offer expires 30 days after the publication’s release. This automatic discount is not intended for use by book distributors or wholesalers.
  Browse Titles
Books
Journals
e-Collections
- - e-Collections
  - Transformative Open Access (Read & Publish)
Open Access
Publish with Us
Resources
- - Instructors
  - Course Adoption
  - Teaching Cases
  - K-12 Online Learning Collection
  - Authors and Editors
  - eEditorial Discovery^® System
  - Peer Review Process
  - Ethics and Malpractice
  - COPE Membership
  - Fair Use Policy
  - Open Access Publishing
  - Author Services
  - FAQ
Catalogs
About Us
Newsroom

A Selective Sparse Coding Model with Embedded Attention Mechanism

Qingyong Li (Beijing Jiaotong University, China), Zhiping Shi (Chinese Academy of Sciences, China) and Zhongzhi Shi (Chinese Academy of Sciences, China)

Source Title: International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) 1(4)

DOI: 10.4018/jcini.2007100105

OnDemand PDF Download:

Available

$37.50

Current Special Offers

No Current Special Offers

Abstract

Sparse coding theory demonstrates that the neurons in primary visual cortex form a sparse representation of natural scenes in the viewpoint of statistics, but a typical scene contains many different patterns (corresponding to neurons in cortex) competing for neural representation because of the limited processing capacity of the visual system. We propose an attention-guided sparse coding model (AGSC). This model includes two modules: non-uniform sampling module simulating the process of retina and data-driven attention module based on the response saliency (RS). Our experiment results show that the model notably decreases the number of coefficients that may be activated and retains the main vision information at the same time. It provides a way to improve the coding efficiency for sparse coding model and to achieve good performance in both population sparseness and lifetime sparseness.

Complete Article List

Search this Journal:

Reset

Volume 16: 1 Issue (2022)

Volume 15: 4 Issues (2021)

Volume 14: 4 Issues (2020)

Volume 13: 4 Issues (2019)

Volume 12: 4 Issues (2018)

Volume 11: 4 Issues (2017)

Volume 10: 4 Issues (2016)

Volume 9: 4 Issues (2015)

Volume 8: 4 Issues (2014)

Volume 7: 4 Issues (2013)

Volume 6: 4 Issues (2012)

Volume 5: 4 Issues (2011)

Volume 4: 4 Issues (2010)

Volume 3: 4 Issues (2009)

Volume 2: 4 Issues (2008)

Volume 1: 4 Issues (2007)

View Complete Journal Contents Listing

MLA

APA

Chicago

Export Reference

A Selective Sparse Coding Model with Embedded Attention Mechanism

Abstract

Complete Article List