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 re- gions on the path linking the leaf to the root. We con- struct region trees by using a high-performance segmen- tation 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.

• Type: Conference
• Year: 2009
• Where: ICCV
• Authors: Joseph J. Lim, Pablo Arbelaez, Chunhui Gu, and Jitendra Malik
• Keywords: Computer Vision, ICCV 2009, Region Ancestry