Skip to main navigation Skip to search Skip to main content

Two-stage saliency detection based on continuous CRF and sparse coding

  • Qiyang Zhao*
  • , Fan Wang
  • , Weibo Li
  • , Baolin Yin
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In the state-of-the-art saliency detection methods based on contrast priors, little attention is paid on the region smoothness constraints. The paper proposes a two-stage saliency detection method in which a smoothness prior is explicitly involved in a continuous Conditional Random Field (CRF). In stage one, we construct a continuous CRF based on the sparse codes of perceptual features on all locations, and minimize the energy of CRF to obtain discrimination maps. In stage two, we train a discriminative machine and learn the saliency maps from discrimination maps, aiming to take the human attention priors into consideration. Our experiments on MSRA-1000 show that the new method is effective against the state-of-the-art methods.

Original languageEnglish
Title of host publicationPattern Recognition - 6th Chinese Conference, CCPR 2014, Proceedings
EditorsShutao Li, Yaonan Wang, Chenglin Liu
PublisherSpringer Verlag
Pages455-463
Number of pages9
ISBN (Electronic)9783662456453
DOIs
StatePublished - 2014
Event6th Chinese Conference on Pattern Recognition, CCPR 2014 - Changsha, China
Duration: 17 Nov 201419 Nov 2014

Publication series

NameCommunications in Computer and Information Science
Volume483
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference6th Chinese Conference on Pattern Recognition, CCPR 2014
Country/TerritoryChina
CityChangsha
Period17/11/1419/11/14

Keywords

  • Continuous CRF
  • Saliency
  • Sparse coding

Fingerprint

Dive into the research topics of 'Two-stage saliency detection based on continuous CRF and sparse coding'. Together they form a unique fingerprint.

Cite this