Momen(e)t: Flavor the Moments in Learning to Classify Shapes

December 18, 2018 Β· Declared Dead Β· πŸ› 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Mor Joseph-Rivlin, Alon Zvirin, Ron Kimmel arXiv ID 1812.07431 Category cs.CG: Computational Geometry Cross-listed cs.LG Citations 76 Venue 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) Last Checked 1 month ago
Abstract
A fundamental question in learning to classify 3D shapes is how to treat the data in a way that would allow us to construct efficient and accurate geometric processing and analysis procedures. Here, we restrict ourselves to networks that operate on point clouds. There were several attempts to treat point clouds as non-structured data sets by which a neural network is trained to extract discriminative properties. The idea of using 3D coordinates as class identifiers motivated us to extend this line of thought to that of shape classification by comparing attributes that could easily account for the shape moments. Here, we propose to add polynomial functions of the coordinates allowing the network to account for higher order moments of a given shape. Experiments on two benchmarks show that the suggested network is able to provide state of the art results and at the same token learn more efficiently in terms of memory and computational complexity.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Computational Geometry

R.I.P. πŸ‘» Ghosted

Dynamic Planar Convex Hull

Riko Jacob, Gerth StΓΈlting Brodal

cs.CG πŸ› The 43rd Annual IEEE Symposium on Foundations of Computer Science, 2002. Proceedings. πŸ“š 240 cites 7 years ago

Died the same way β€” πŸ‘» Ghosted