RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down features论文笔记
openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w40/Shigematsu_Learning_RGB-D_Salient_ICCV_2017_paper.pdf研究背景深度神经网络因较可以较好的将自顶向下的特征和低维度特征结合起来