| 内容提要: |
We propose a general CNN-based multi-modal learning framework for RGB-D object recognition. We first construct deep CNN layers for color and depth separately, which are then connected with a carefully designed multi-model layer. The result of the multi-model layer are back-propagated to update parameters of CNN layers. Experimental results on two widely used RGB-D object datasets show that our method for general multi-modal learning achieves comparable performance to state-of-the-art methods specifically designed for RGB-D data. |