State-of-the-Art in Visual Attention Modeling
State-of-the-Art in Visual Attention Modeling
复制标题
DOI：
10.1109/tpami.2012.89
复制
发表时间：
2013-01-01
影响因子：
23.6
通讯作者：
Itti, Laurent
中科院分区：
文献类型：
--
作者：
Borji, Ali;Itti, Laurent
在过去的25年中，对视觉关注局部刺激驱动的，显着性的注意力HA是一个非常活跃的研究领域。现在有许多不同的关注模型，除了对其他领域的理论贡献外，还可以在计算机视觉，移动机器人技术和认知系统中成功应用。在这里，我们从计算的角度回顾了这些模型中实现的基本关注概念。我们提出了近65个模型的分类学，该分类学对方法，功能和缺点进行了批判性比较。特别是，制定了从行为和计算研究得出的13个标准，用于对注意模型的定性比较。此外，我们解决了模型的几个具有挑战性的问题，包括计算的生物学合理性，与眼动数据集的相关性，自下而上和自上而下的分离以及构建有意义的绩效指标。最后，我们重点介绍了注意建模的当前研究趋势，并为未来提供了见解。
Modeling visual attention-particularly stimulus-driven, saliency-based attention-has been a very active research area over the past 25 years. Many different models of attention are now available which, aside from lending theoretical contributions to other fields, have demonstrated successful applications in computer vision, mobile robotics, and cognitive systems. Here we review, from a computational perspective, the basic concepts of attention implemented in these models. We present a taxonomy of nearly 65 models, which provides a critical comparison of approaches, their capabilities, and shortcomings. In particular, 13 criteria derived from behavioral and computational studies are formulated for qualitative comparison of attention models. Furthermore, we address several challenging issues with models, including biological plausibility of the computations, correlation with eye movement datasets, bottom-up and top-down dissociation, and constructing meaningful performance measures. Finally, we highlight current research trends in attention modeling and provide insights for future.