Loading...
Please wait, while we are loading the content...
Bayesian Learning Based Visual Saliency Detection
| Content Provider | Semantic Scholar |
|---|---|
| Author | Zhang, Jinxia Ding, Jundi Liu, Chuancai Yang, Jingyu |
| Copyright Year | 2012 |
| Abstract | This paper is to present a Bayesian learning based framework for visual saliency detection in natural scenes. Especially, for any point in the scene, this framework has considered whether it is salient or not; but previous methods by Bayesian learning seem not to do so. This framework includes two steps. First, the framework indicates that visual saliency is constituted with three main saliency modules. In a free-viewing manner, these main saliency modules are rarity, distinctiveness and central bias. Second, they are non-linearly combined for the final saliency map by a regularized neural network. The experimental results on two fixation datasets indicate that our framework outperforms other representative methods. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.researchgate.net/profile/Chuancai_Liu3/publication/261076126_Bayesian_learning_based_visual_saliency_detection/links/545593990cf26d5090a6ffbc.pdf |
| Alternate Webpage(s) | https://www.researchgate.net/profile/Chuancai_Liu3/publication/261076126_Bayesian_learning_based_visual_saliency_detection/links/545593990cf26d5090a6ffbc.pdf |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Artificial neural network Biological Neural Networks Bottom-up parsing Exponent bias Natural Science Disciplines Neural Network Simulation |
| Content Type | Text |
| Resource Type | Article |
