Top-down saliency with Locality-constrained Contextual Sparse Coding

We propose a locality-constrained contextual sparse coding (LCCSC) for top-down saliency estimation where higher saliency scores are assigned to the image locations corresponding to the target object. Three locality constraints are integrated in to this novel sparse coding. First is the spatial or contextual locality constraint in which features from adjacent regions have similar code, second is the feature-domain locality constraint in which similar features have similar code, and third is the category-domain locality constraint in which features are coded using similar atoms from each partition of the dictionary, where each partition corresponds to an object category.