Context by region ancestry

In this paper, we introduce a new approach for modeling visual context. For this purpose, we consider the leaves of a hierarchical segmentation tree as elementary units. Each leaf is described by features of its ancestral set, the regions on the path linking the leaf to the root. We construct region trees by using a high-performance segmentation method. We then learn the importance of different descriptors (e.g. color, texture, shape) of the ancestors for classification. We report competitive results on the MSRC segmentation dataset and the MIT scene dataset, showing that region ancestry efficiently encodes information about discriminative parts, objects and scenes.

1. Introduction

The role of context in visual perception has been studied for a long time in psychology [20], [3], [11]. Visual context can be defined by the scene embedding a particular object [20], and by the semantic relations among different objects [3]. Thus, contextual information for a table is provided by the dining room where it lies, but also by the presence of chairs around it and dishes on its top.