Context-Aware Saliency Detection

Technion – Israel Institute of Technology · OASIS Clinic

PubMed
Indexed incrossrefpubmed

Abstract

We propose a new type of saliency—context-aware saliency—which aims at detecting the image regions that represent the scene. This definition differs from previous definitions whose goal is to either identify fixation points or detect the dominant object. In accordance with our saliency definition, we present a detection algorithm which is based on four principles observed in the psychological literature. The benefits of the proposed approach are evaluated in two applications where the context of the dominant objects is just as essential as the objects themselves. In image retargeting, we demonstrate that using our saliency prevents distortions in the important regions. In summarization, we show that our…

Citation impact

1,582
total citations
FWCI
47.61
Percentile
100%
References
37
Citations per year

Authors

3

Topics & keywords

Keywords
  • Automatic summarization
  • Computer science
  • Artificial intelligence
  • Seam carving
  • Context (archaeology)
  • Object detection
  • Image (mathematics)
  • Computer vision
UN Sustainable Development Goals
  • Reduced inequalities
No related works found for this paper.