Name
Abstract | ||
|---|---|---|
In this paper, we propose a saliency detection model for RGB-D images based on the deep features of RGB images and depth images within a Bayesian framework. By analysing 3D saliency in the case of RGB images and depth images, the class-conditional mutual information is computed for measuring the dependence of deep features extracted using a convolutional neural network; then, the posterior probability of the RGB-D saliency is formulated by applying Bayes’ theorem. By assuming that deep features are Gaussian distributions, a discriminative mixed-membership naive Bayes (DMNB) model is used to calculate the final saliency map. The Gaussian distribution parameters can be estimated in the DMNB model by using a variational inference-based expectation maximization algorithm. The experimental results on RGB-D images from the NLPR dataset and NJU-DS400 dataset show that the proposed model performs better than other existing models. |
Year | Venue | Keywords |
|---|---|---|
2018 | IPSJ Trans. Computer Vision and Applications | Bayesian fusion, Deep learning, Generative model, Saliency detection, RGB-D images |
Field | DocType | Volume |
Computer vision,Naive Bayes classifier,Pattern recognition,Expectation–maximization algorithm,Posterior probability,Mutual information,Artificial intelligence,Discriminative model,Mathematics,Generative model,Bayesian probability,Bayes' theorem | Journal | 10 |
Citations | PageRank | References |
2 | 0.38 | 20 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Songtao Wang | 1 | 2 | 0.38 |
| Zhen Zhou | 2 | 2 | 1.06 |
| Wei Jin | 3 | 83 | 25.25 |
| Han-Bing Qu | 4 | 4 | 1.79 |