Name
Abstract | ||
|---|---|---|
Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches. While CNNs naturally extend to other domains, such as audio and video, where data is also organized in rectangular grids, they do not easily generalize to other types of data such as 3D shape meshes, social network graphs or molecular graphs. To handle such data, we propose a novel graph-convolutional network architecture that builds on a generic formulation that relaxes the 1-to-1 correspondence between filter weights and data elements around the center of the convolution. The main novelty of our architecture is that the shape of the filter is a function of the features in the previous network layer, which is learned as an integral part of the neural network. Experimental evaluations on digit recognition, semi-supervised document classification, and 3D shape correspondence yield state-of-the-art results, significantly improving over previous work for shape correspondence. |
Year | Venue | Field |
|---|---|---|
2017 | arXiv: Computer Vision and Pattern Recognition | Document classification,Polygon mesh,Convolutional neural network,Computer science,Convolution,Network layer,Network architecture,Theoretical computer science,Data type,Artificial neural network |
DocType | Volume | Citations |
Journal | abs/1706.05206 | 1 |
PageRank | References | Authors |
0.36 | 15 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nitika Verma | 1 | 1 | 0.36 |
| Edmond Boyer | 2 | 2758 | 130.84 |
| J. J. Verbeek | 3 | 3944 | 181.44 |