/D-CNN

Depth CNNs for RGB-D Scene Recognition: Learning From Scratch Better Than Transferring From RGB-CNNs

D-CNN

Depth CNNs for RGB-D Scene Recognition: Learning From Scratch Better Than Transferring From RGB-CNNs

This project contains two Caffe CNN models and deploy files, i.e., WSP and D-CNN, which are proposed in the AAAI2017 paper. If you use the pre-trained CNN models, please cite the following paper:

Xinhang Song, Luis Herranz, Shuqiang Jiang. “Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs” Thirty-First AAAI Conference on Artificial Intelligence (2017)