Abstract | ||
---|---|---|
Exploring effective 3D shape recognition algorithms attracts much research attention recently. The existing multiview-based 3D shape recognition methods usually ignore the local information exploration in each view image. In this article, we propose a novel local information-based multiattention network, which concentrates the effective information in the feature maps and captures the view-wise in... |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/MMUL.2021.3136238 | IEEE MultiMedia |
Keywords | DocType | Volume |
Shape,Three-dimensional displays,Feature extraction,Solid modeling,Correlation,Visualization,Training | Journal | 29 |
Issue | ISSN | Citations |
1 | 1070-986X | 0 |
PageRank | References | Authors |
0.34 | 9 | 5 |