Attention selection and recognition in scene viewing (B05)

场景观看中的注意选择与识别（B05）

• 批准号: 387131476
• 金额: --
• 依托单位: Institut für Informatik und Computational Science
• 依托单位国家: 德国
• 项目类别: Collaborative Research Centres
• 财政年份: 2017
• 资助国家: 德国
• 起止时间: 2016-12-31 至 2020-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/387131476?language=en
• 关键词: Attention; selection; recognition; scene; viewing

The first principal goal of the project is to develop models of attentional selection in scene viewing that account for the viewer’s familiarity with a visual scene and for conceptually-driven anticipation of the image content as well as for viewer-specific distributional properties of fixational patterns. The second principal goal is to leverage these generative models of fixation sequences into discriminative models that accurately predict values of latent variables, such as levels of familiarity, based on a given fixation sequence. We will study to which extent the familiarity of a viewer with a given face or a given technical diagram can beassessed given the sequence of eye fixations. Such models would have wide-ranging applications in e-learning, criminology, and other areas.

该项目的第一个主要目标是开发场景观看中的注意选择模型，该模型考虑到观看者对视觉场景的熟悉程度、对图像内容的概念驱动的预期以及注视模式的特定于观看者的分布特性。第二个主要目标是利用这些凝视序列的生成模型来识别模型，该模型基于给定的凝视序列准确地预测潜在变量的值，例如熟悉度。我们将研究在多大程度上可以评估观众对给定面孔或给定技术图表的熟悉程度，因为给定了眼睛注视的顺序。这种模式将在电子学习、犯罪学和其他领域有广泛的应用。