BMVC 2004, Kingston, 7th-9th Sept, 2004
Quantifying Temporal Saliency
H. Hung and S. Gong (Queen Mary, University of London)
A significant problem in automatic scene interpretation is the ability to perform
contextually meaningful segmentation of both static and moving images
using a bottom-up approach. We examine and propose an extension to Kadir
and Brady�s Scale Saliency Algorithm for quantifying temporal saliency and
performing automatic spatial and temporal scale selection.