Torralba Antonio, Oliva Aude, Castelhano Monica S, Henderson John M
Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
Psychol Rev. 2006 Oct;113(4):766-86. doi: 10.1037/0033-295X.113.4.766.
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 (scene-centered) 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.
许多实验表明，人类视觉系统广泛利用上下文信息来促进在自然场景中的目标搜索。然而，如何对上下文影响进行形式化建模的问题仍然悬而未决。基于贝叶斯框架，作者提出了一种由全局场景上下文进行注意力引导的原创方法。该模型包括两条并行路径；一条路径计算局部特征（显著性），另一条路径计算全局（以场景为中心）特征。注意力的上下文引导模型在视觉处理的早期阶段结合了自下而上的显著性、场景上下文和自上而下的机制，并预测在现实世界场景中执行自然搜索任务的人类观察者可能会注视的图像区域。
