Abstract | ||
---|---|---|
A key problem in salient object detection is how to effectively model the semantic properties of salient objects in a data-driven manner. In this paper, we propose a multi-task deep saliency model based on a fully convolutional neural network with global input (whole raw images) and global output (whole saliency maps). In principle, the proposed saliency model takes a data-driven strategy for enco... |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/TIP.2016.2579306 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Semantics,Object detection,Image segmentation,Feature extraction,Neural networks,Convolution,Computational modeling,Regression analysis | Object detection,Computer vision,Viola–Jones object detection framework,Pattern recognition,Salience (neuroscience),Convolutional neural network,Computer science,Feature extraction,Image segmentation,Artificial intelligence,Artificial neural network,Feature learning | Journal |
Volume | Issue | ISSN |
25 | 8 | 1057-7149 |
Citations | PageRank | References |
145 | 3.19 | 48 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xi Li | 1 | 1850 | 137.71 |
Liming Zhao | 2 | 175 | 6.01 |
lina wei | 3 | 152 | 6.62 |
Yang Ming-Hsuan | 4 | 15303 | 620.69 |
Fei Wu | 5 | 2209 | 153.88 |
Yue-Ting Zhuang | 6 | 3549 | 216.06 |
Haibin Ling | 7 | 4531 | 215.76 |
Jingdong Wang | 8 | 4198 | 156.76 |