Saliency based joint topic discovery for object categorization
Zhidong Li, Yang Wang, Glenn Geers, Jing Chen, Jun Yang, John E. Laird · 2010
We present a novel approach of saliency based image categorization using topic model. In each image, salient foreground objects are discriminated from background scene by saliency detection. Then topic model is used to jointly discover topics of foreground and background. Our approach can categorize images in a completely unsupervised manner and achieve higher performance than previous categorization methods, especially for those images with similar foreground/background.