A Statistical Model for General Contextual Object Recognition

We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects. Given a set of images and their associated text (e.g. keywords, captions, descriptions), the objective is to segment an image, in either a crude or sophisticated fashion, then to find the proper associations between words and regions. Previous models are limited by the scope of the representation. In particular, they fail to exploit spatial context in the images and words. We develop a more expressive model that takes this into account. We formulate a spatially consistent probabilistic mapping between continuous image feature vectors and the supplied word tokens. By learning both word-to-region associations and object relations, the proposed model augments scene segmentations due to smoothing implicit in spatial consistency. Context introduces cycles to the undirected graph, so we cannot rely on a straightfo...

• Type: Conference
• Year: 2004
• Where: ECCV
• Authors: Peter Carbonetto, Nando de Freitas, Kobus Barnard
• Keywords: Approximate Em Algorithm, Computer Vision, Context Introduces Cycles, Discrete Object Representation, ECCV 2004, Spatial Consistency, Spatial Context