DMCA
Contextual guidance of eye movements and attention in real-world scenes: The role of global features in object search (2006)
Cached
Download Links
| Venue: | PSYCHOLOGICAL REVIEW |
| Citations: | 257 - 17 self |
BibTeX
@ARTICLE{Torralba06contextualguidance,
author = {Antonio Torralba and Aude Oliva and Monica S. Castelhano and John M. Henderson},
title = {Contextual guidance of eye movements and attention in real-world scenes: The role of global features in object search},
journal = {PSYCHOLOGICAL REVIEW},
year = {2006},
volume = {113},
number = {4},
pages = {766--786}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Many experiments have shown that the human visual system makes extensive use of contextual information for facilitating object search in natural scenes. However, the question of how to formally model contextual influences is still open. On the basis of a Bayesian framework, the authors present an original approach of attentional guidance by global scene context. The model comprises 2 parallel pathways; one pathway computes local features (saliency) and the other computes global (scenecentered) features. The contextual guidance model of attention combines bottom-up saliency, scene context, and top-down mechanisms at an early stage of visual processing and predicts the image regions likely to be fixated by human observers performing natural search tasks in real-world scenes.
Keyphrases
real-world scene object search global feature eye movement contextual guidance human observer many experiment parallel pathway extensive use human visual system image region contextual information original approach natural scene attention combine bottom-up saliency visual processing early stage contextual influence natural search task scene context attentional guidance contextual guidance model top-down mechanism global scene context bayesian framework local feature
