Using Dependent Regions for Object Categorization in a Generative Framework

"Bag of words" models have enjoyed much attention and achieved good performances in recent studies of object categorization. In most of these works, local patches are modeled as basic building blocks of an image, analogous to words in text documents. In most previous works using the "bag of words" models (e.g. [4, 20, 7]), the local patches are assumed to be independent with each other. In this paper, we relax the independence assumption and model explicitly the inter-dependency of the local regions. Similarly to previous work , we represent images as a collection of patches, each of which belongs to a latent "theme" that is shared across images as well as categories. We learn the theme distributions and patch distributions over the themes in a hierarchical structure [22]. In particular, we introduce a linkage structure over the latent themes to encode the dependencies of the patches. This structure enforces the semantic connections among the patches by f...

• Type: Conference
• Year: 2006
• Where: CVPR
• Authors: Gang Wang, Ye Zhang, Fei-Fei Li 0002
• Keywords: Caltech 101 Datasets, Computer Vision, CVPR 2006, Latent Themes, Local Patches, Object Categorization, Object Category Datasets