Abstract | ||
---|---|---|
In this letter, we propose a novel saliency model for saliency detection, named sparse-distinctive (SD) saliency model. Different from the existing models that only consider sparsity or distinctness of image, the proposed model computes saliency based on sparsity and distinctness. The basic idea is that sparsity and distinctness contribute to saliency simultaneously and play different roles under different scenes. This sparse-distinctive saliency model is based on some key ideas introduced in this letter and supported by psychological evidence. Experimental results on public benchmark eye-tracking datasets show that considering the sparsity and distinctness for saliency can improve the accuracy of predicting human fixations, and the proposed model outperforms the mainstream models on predicting human fixations. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/LSP.2014.2382755 | IEEE Signal Process. Lett. |
Keywords | Field | DocType |
public benchmark eye-tracking datasets,distinctness,human fixations,feature extraction,visual attention,object detection,saliency,sparsity,sparse-distinctive saliency detection,visualization,fourier transforms,predictive models,computational modeling,psychology | Fixation (psychology),Kadir–Brady saliency detector,Pattern recognition,Salience (neuroscience),Visualization,Computer science,Visual attention,Artificial intelligence,Distinctness of image,Machine learning | Journal |
Volume | Issue | ISSN |
22 | 9 | 1070-9908 |
Citations | PageRank | References |
0 | 0.34 | 22 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yongkang Luo | 1 | 5 | 4.56 |
Peng Wang | 2 | 31 | 8.02 |
Wenjun Zhu | 3 | 18 | 4.98 |
Hong Qiao | 4 | 1147 | 110.95 |