How important is location in saliency detection

Tongwei Ren, Ran Ju, Yan Liu, Gangshan Wu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

4 Citations (Scopus)


Current saliency detection methods mainly work on exploring the potential of low-level and high-level visual features, such as color, texture and face, but treat location information as a weak assistance or completely ignore it. In this paper, we reveal the importance of location information in saliency detection. We analyze the largest public image dataset for saliency detection THUS10000, and find the relationship between content location and saliency distribution. To further validate the effect of location information, we propose two location based saliency detection approaches, location based Gaussian distribution and location based saliency propagation, which make use of no or weak assistance of image content. Experimental results show that location based saliency detection can obtain much better performance than random selection, even better than most state-of-the-art saliency detection methods.
Original languageEnglish
Title of host publicationICIMCS 2014 - Proceedings of the 6th International Conference on Internet Multimedia Computing and Service
PublisherAssociation for Computing Machinery
Number of pages4
ISBN (Print)9781450328104
Publication statusPublished - 1 Jan 2014
Event6th International Conference on Internet Multimedia Computing and Service, ICIMCS 2014 - Xiamen, China
Duration: 10 Jul 201412 Jul 2014


Conference6th International Conference on Internet Multimedia Computing and Service, ICIMCS 2014


  • Location information
  • Patch representation
  • Saliency detection
  • Saliency propagation

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software


Dive into the research topics of 'How important is location in saliency detection'. Together they form a unique fingerprint.

Cite this