Image interpretation above and below the object level
Image interpretation above and below the object level
复制标题
DOI：
10.1098/rsfs.2018.0020
复制
发表时间：
2018-08-06
期刊：
影响因子：
4.4
通讯作者：
Ullman, Shimon
中科院分区：
文献类型：
--
作者：
Ben-Yosef, Guy;Ullman, Shimon
视觉计算模型近年来发展迅速，在某些领域可以与人类水平的性能相媲美。到目前为止，大部分的进展都集中在分析视觉场景中的对象级别的识别和定位的场景中的对象。人类对图像的理解达到了更丰富和更深入的图像理解，既包括对象级别的“下方”，例如识别和定位对象部分和子部分，也包括对象级别的“上方”，例如识别对象关系，以及具有其动作和交互的代理。在这两种情况下，理解取决于恢复图像中有意义的结构及其组成部分、性质和相互关系，这一过程在此称为“图像解释”。在本文中，我们描述了最近的方向，人类和计算机视觉研究的基础上，对人性化的图像解释，超出了目前的计划，无论是在对象水平，以及图像解释的一些方面，在有意义的配置超出了个别对象的识别水平，特别是，两个人之间的密切接触的互动。在这两种情况下，识别过程取决于对所谓的“最小图像”的详细解释，在这两个层次上，识别取决于结合“自下而上"的处理，从低到高的处理层次，以及”自上而下“的处理，从高到低的视觉分析阶段。
Computational models of vision have advanced in recent years at a rapid rate, rivalling in some areas human-level performance. Much of the progress to date has focused on analysing the visual scene at the object level-the recognition and localization of objects in the scene. Human understanding of images reaches a richer and deeper image understanding both 'below' the object level, such as identifying and localizing object parts and sub-parts, as well as 'above' the object level, such as identifying object relations, and agents with their actions and interactions. In both cases, understanding depends on recovering meaningful structures in the image, and their components, properties and inter-relations, a process referred here as ` image interpretation'. In this paper, we describe recent directions, based on human and computer vision studies, towards human-like image interpretation, beyond the reach of current schemes, both below the object level, as well as some aspects of image interpretation at the level of meaningful configurations beyond the recognition of individual objects, and in particular, interactions between two people in close contact. In both cases the recognition process depends on the detailed interpretation of so-called 'minimal images', and at both levels recognition depends on combining 'bottom-up' processing, proceeding from low to higher levels of a processing hierarchy, together with 'top-down' processing, proceeding from high to lower levels stages of visual analysis.