Abstract | ||
---|---|---|
We present a new method of predicting the visually salient locations in an image. The basic idea is to use the sparse coding coefficients as features and find a way to reconstruct the sparse features into a saliency map. In the training phase, we use the images and the corresponding fixation values to train a feature-based dictionary for sparse coding as well as a fixation-based dictionary for converting the sparse coefficients into a saliency map. In the test phase, given a new image, we can get its sparse coding from the feature-based dictionary and then estimate the saliency map using the fixation-based dictionary. We evaluate our results on two datasets with the shuffled AUC score and show that our method is effective in deriving the saliency map from sparse coding information. |
Year | Venue | Keywords |
---|---|---|
2012 | Signal & Information Processing Association Annual Summit and Conference | dictionaries,image coding,learning (artificial intelligence),feature-based dictionary,fixation values,fixation-based dictionary,learning sparse dictionaries,saliency detection,saliency map,sparse coding coefficients,sparse features,training phase,visually salient locations |
Field | DocType | ISSN |
Computer vision,Saliency map,K-SVD,Pattern recognition,Salience (neuroscience),Neural coding,Computer science,Sparse approximation,Image coding,Artificial intelligence,Salient | Conference | 2309-9402 |
ISBN | Citations | PageRank |
978-1-4673-4863-8 | 1 | 0.36 |
References | Authors | |
10 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Karen Guo | 1 | 1 | 0.36 |
Hwann-Tzong Chen | 2 | 826 | 52.13 |