Title | ||
---|---|---|
SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With Attention. |
Abstract | ||
---|---|---|
Learning 3D global features by aggregating multiple views has been introduced as a successful strategy for 3D shape analysis. In recent deep learning models with end-to-end training, pooling is a widely adopted procedure for view aggregation. However, pooling merely retains the max or mean value over all views, which disregards the content information of almost all views and also the spatial infor... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TIP.2018.2868426 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Three-dimensional displays,Shape,Machine learning,Solid modeling,Training,Semantics,Recurrent neural networks | Pattern recognition,Pooling,Recurrent neural network,Artificial intelligence,Overfitting,Deep learning,Discriminative model,Mathematics,Semantics,Shape analysis (digital geometry),Encoding (memory) | Journal |
Volume | Issue | ISSN |
28 | 2 | 1057-7149 |
Citations | PageRank | References |
28 | 0.90 | 14 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Han Zhizhong | 1 | 198 | 18.28 |
Mingyang Shang | 2 | 42 | 3.09 |
Zhenbao Liu | 3 | 364 | 24.08 |
Chi-Man Vong | 4 | 557 | 41.41 |
Yu-shen Liu | 5 | 319 | 23.20 |
Zwicker Matthias | 6 | 2513 | 129.25 |
Junwei Han | 7 | 3501 | 194.57 |
C. L. Philip Chen | 8 | 4022 | 244.76 |