Abstract | ||
---|---|---|
In this paper, we propose a bottom-up saliency model based on absorbing Markov chain (AMC). First, a sparsely connected graph is constructed to capture the local context information of each node. All image boundary nodes and other nodes are, respectively, treated as the absorbing nodes and transient nodes in the absorbing Markov chain. Then, the expected number of times from each transient node to... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TIP.2017.2766787 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Markov processes,Transient analysis,Feature extraction,Object detection,Computational modeling,Sparse matrices,Image segmentation | Computer vision,Markov process,Pattern recognition,Stochastic matrix,Salience (neuroscience),Matrix (mathematics),Image segmentation,Artificial intelligence,Connectivity,Mathematics,Absorbing Markov chain,Sparse matrix | Journal |
Volume | Issue | ISSN |
27 | 2 | 1057-7149 |
Citations | PageRank | References |
15 | 0.55 | 42 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lihe Zhang | 1 | 1372 | 38.73 |
Jianwu Ai | 2 | 15 | 0.89 |
Bowen Jiang | 3 | 221 | 5.78 |
Huchuan Lu | 4 | 4827 | 186.26 |
Xiukui Li | 5 | 15 | 0.55 |