Multi-modal fusion network with multi-scale multi-path and cross-modal interactions for RGB-D salient object detection

作者：

Highlights：

• Using CNNs to fuse RGB and depth data with only single path is not sufficient.

• Both global reasoning and local capturing are important for saliency detection.

• Bottom-up cross-modal interactions are also beneficial for learning complements.

摘要

•Using CNNs to fuse RGB and depth data with only single path is not sufficient.•Both global reasoning and local capturing are important for saliency detection.•Bottom-up cross-modal interactions are also beneficial for learning complements.

论文关键词：RGB-D,Convolutional neural networks,Multi-path,Saliency detection

论文评审过程：Received 4 July 2017, Revised 19 April 2018, Accepted 12 August 2018, Available online 13 August 2018, Version of Record 2 November 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.08.007