VERAM : View-Enhanced Recurrent Attention Model for 3D Shape Classification
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, e.g., multi-view active object recognition by a robot. This pap...
Ausführliche Beschreibung
Bibliographische Detailangaben
Veröffentlicht in: | IEEE transactions on visualization and computer graphics. - 1996. - 25(2019), 12 vom: 20. Dez., Seite 3244-3257
|
1. Verfasser: |
Chen, Songle
(VerfasserIn) |
Weitere Verfasser: |
Zheng, Lintao,
Zhang, Yan,
Sun, Zhixin,
Xu, Kai |
Format: | Online-Aufsatz
|
Sprache: | English |
Veröffentlicht: |
2019
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on visualization and computer graphics
|
Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |