Title | ||
---|---|---|
3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN with Hierarchical Attention Aggregation. |
Abstract | ||
---|---|---|
Learning 3D global features by aggregating multiple views is important. Pooling is widely used to aggregate views in deep learning models. However, pooling disregards a lot of content information within views and the spatial relationship among the views, which limits the discriminability of learned features. To resolve this issue, 3D to Sequential Views (3D2SeqViews) is proposed to more effectivel... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TIP.2019.2904460 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Three-dimensional displays,Shape,Deep learning,Solid modeling,Feature extraction,Aggregates,Convolutional neural networks | View integration,Pattern recognition,Convolutional neural network,Pooling,Spatial relationship,Artificial intelligence,Deep learning,Discriminative model,Machine learning,Feature learning,Recursion,Mathematics | Journal |
Volume | Issue | ISSN |
28 | 8 | 1057-7149 |
Citations | PageRank | References |
15 | 0.53 | 17 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Han Zhizhong | 1 | 198 | 18.28 |
Honglei Lu | 2 | 15 | 0.53 |
Zhenbao Liu | 3 | 364 | 24.08 |
Chi-Man Vong | 4 | 557 | 41.41 |
Yu-Shen Liu | 5 | 23 | 2.05 |
Zwicker Matthias | 6 | 2513 | 129.25 |
Junwei Han | 7 | 3501 | 194.57 |
C L Philip Chen | 8 | 698 | 34.35 |