Publications
Detailed Information
High-dimensional convolutional networks for geometric pattern recognition
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choy, Christopher | - |
dc.contributor.author | Lee, Junha | - |
dc.contributor.author | Ranftl, René | - |
dc.contributor.author | Park, Jaesik | - |
dc.contributor.author | Koltun, Vladlen | - |
dc.date.accessioned | 2024-05-09T04:13:20Z | - |
dc.date.available | 2024-05-09T04:13:20Z | - |
dc.date.created | 2024-05-08 | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.11224-11233 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | https://hdl.handle.net/10371/201308 | - |
dc.description.abstract | Many problems in science and engineering can be formulated in terms of geometric patterns in high-dimensional spaces. We present high-dimensional convolutional networks (ConvNets) for pattern recognition problems that arise in the context of geometric registration. We first study the effectiveness of convolutional networks in detecting linear subspaces in high-dimensional spaces with up to 32 dimensions: much higher dimensionality than prior applications of ConvNets. We then apply high-dimensional ConvNets to 3D registration under rigid motions and image correspondence estimation. Experiments indicate that our high-dimensional ConvNets outperform prior approaches that relied on deep networks based on global pooling operators. | - |
dc.language | 영어 | - |
dc.publisher | IEEE | - |
dc.title | High-dimensional convolutional networks for geometric pattern recognition | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/CVPR42600.2020.01124 | - |
dc.citation.journaltitle | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.identifier.scopusid | 2-s2.0-85094119233 | - |
dc.citation.endpage | 11233 | - |
dc.citation.startpage | 11224 | - |
dc.description.isOpenAccess | Y | - |
dc.contributor.affiliatedAuthor | Park, Jaesik | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.