Abstract | ||
---|---|---|
•We propose the CAN architecture to learn discriminative feature representations for saliency detection in RGB D images, by modeling multi modal and multi scale context dependencies within the context aware fusion and context dependent deconvolution. It is demonstrated that the proposed end to end CAN can a chieve favourable performance compared with state of the art methods.•A context aware fusion unit based on the LSTM architecture (MCFLSTM) is developed to learn complementary contexts from two modalities. The positive effect of this fusion approach is demonstrated experimentally.•A hierarchical LSTM structure called HSCLSTM is proposed to progressively refine saliency cues by modelling the context dependencies among different scales. Its effectiveness is also verified by experimental results. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.patcog.2020.107630 | Pattern Recognition |
Keywords | DocType | Volume |
Stereoscopic saliency analysis,3D images,Multi-modal context fusion,Context-dependent deconvolution | Journal | 111 |
Issue | ISSN | Citations |
1 | 0031-3203 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fangfang Liang | 1 | 9 | 1.43 |
Lijuan Duan | 2 | 1 | 2.72 |
Wei Ma | 3 | 9 | 1.77 |
Yuanhua Qiao | 4 | 3 | 2.07 |
Jun Miao | 5 | 220 | 22.17 |
Qixiang Ye | 6 | 913 | 64.51 |