@InProceedings{yoshiyasu:icip:2017,
  author    = {Yoshiyasu, Yusuke and Yoshida, Eiichi and Pirk, Soeren and Guibas, Leonidas},
  title     = {3D Convolutional Neural Networks by Modal Fusion},
  booktitle = {IEEE International Conference on Image Processing},
  year      = {2017},
  pages     = {1777--1781},
  address   = {Beijing, China},
  month     = {September 17-September 20},
  url       = {https://staff.aist.go.jp/e.yoshida/papers/ICIP17\_Yoshiyasu.pdf},
  doi       = {https://doi.org/10.1109/ICIP.2017.8296587},
  abstract  = {We propose multi-view and volumetric convolutional neural networks (ConvNets) for 3D shape recognition, which combines surface normal and height fields to capture local geometry and physical size of an object. This strategy helps distinguishing between objects with similar geometries but different sizes. This is especially useful for enhancing volumetric ConvNets and classifying 3D scans with insufficient surface details. Experimental results on CAD and real-world scandatasetsshowedthatourtechniqueoutperformsprevious approaches}
}