VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Visualization and Computer Graphics"
DOI: 10.1109/tvcg.2018.2866793
Abstract: Multi-view deep neural network is perhaps the most successful approach in 3D shape classification. However, the fusion of multi-view features based on max or average pooling lacks a view selection mechanism, limiting its application in,… read more here.
Keywords: veram view; attention; view; shape classification ... See more keywords