Abstract | ||
---|---|---|
•Designed a multi-scale backward optimization network which can hold both rich inherent features from shallower layers and semantic features from deeper layers, then high-level features are transmitted backward to guiding low-level features.•Deep CRF network is introduced to form the relationships between adjacent pixels which is crucial to improve the quality of saliency maps.•All modules can be conveniently embedded into other Convolutional Neural Networks for feature and relation representation. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.patcog.2020.107266 | Pattern Recognition |
Keywords | DocType | Volume |
Saliency detection,Conditional random field,Convolutional neural network | Journal | 103 |
Issue | ISSN | Citations |
1 | 0031-3203 | 1 |
PageRank | References | Authors |
0.35 | 33 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenliang Qiu | 1 | 5 | 1.08 |
Xinbo Gao | 2 | 5534 | 344.56 |
Bing Han | 3 | 1 | 1.02 |