Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes

Kevin P. Murphy, Antonio Torralba, William T. Freeman

Advances in Neural Information Processing Systems 16 (NIPS 2003)

Standard approaches to object detection focus on local patches of the image, and try to classify them as background or not. We propose to use the scene context (image as a whole) as an extra source of (global) information, to help resolve local ambiguities. We present a conditional random field for jointly solving the tasks of object detection and scene classification.