MSDCNN: A multiscale dilated convolution neural network for fine-grained 3D shape classification
- 23 January 2024
- journal article
- research article
- Published by Elsevier in Neural Networks
- Vol. 172, 106141
Abstract
No abstract availableKeywords
This publication has 28 references indexed in Scilit:
- SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With AttentionIEEE Transactions on Image Processing, 2018
- VERAM: View-Enhanced Recurrent Attention Model for 3D Shape ClassificationIEEE Transactions on Visualization and Computer Graphics, 2018
- SO-Net: Self-Organizing Network for Point Cloud Analysis2018
- RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints2018
- Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models2017
- Aggregated Residual Transformations for Deep Neural Networks2017
- Volumetric and Multi-view CNNs for Object Classification on 3D Data2016
- Rethinking the Inception Architecture for Computer Vision2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- Illumination for computer generated picturesCommunications of the ACM, 1975