Interesting objects are visually salient - PubMed (original) (raw)

Comparative Study

. 2008 Mar 7;8(3):3.1-15.

doi: 10.1167/8.3.3.

Affiliations

Free article

Comparative Study

Interesting objects are visually salient

Lior Elazary et al. J Vis. 2008.

Free article

Abstract

How do we decide which objects in a visual scene are more interesting? While intuition may point toward high-level object recognition and cognitive processes, here we investigate the contributions of a much simpler process, low-level visual saliency. We used the LabelMe database (24,863 photographs with 74,454 manually outlined objects) to evaluate how often interesting objects were among the few most salient locations predicted by a computational model of bottom-up attention. In 43% of all images the model's predicted most salient location falls within a labeled region (chance 21%). Furthermore, in 76% of the images (chance 43%), one or more of the top three salient locations fell on an outlined object, with performance leveling off after six predicted locations. The bottom-up attention model has neither notion of object nor notion of semantic relevance. Hence, our results indicate that selecting interesting objects in a scene is largely constrained by low-level visual properties rather than solely determined by higher cognitive processes.

PubMed Disclaimer

Publication types

MeSH terms

LinkOut - more resources