Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICCV.2009.5459436 | Kyoto |
Keywords | Field | DocType |
image classification,image segmentation,trees (mathematics),MIT scene dataset,MSRC segmentation dataset,ancestral set,hierarchical segmentation tree,high-performance segmentation method,region ancestry,region trees,visual context | Computer vision,Pattern recognition,Segmentation,Computer science,Context model,Image segmentation,Artificial intelligence,Pixel,Contextual image classification,Discriminative model | Conference |
ISSN | ISBN | Citations |
1550-5499 E-ISBN : 978-1-4244-4419-9 | 978-1-4244-4419-9 | 37 |
PageRank | References | Authors |
2.06 | 21 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Joseph J. Lim | 1 | 901 | 51.86 |
Pablo Arbelaez | 2 | 3626 | 173.00 |
Chunhui Gu | 3 | 37 | 2.06 |
Jitendra Malik | 4 | 39445 | 3782.10 |