Matches in SemOpenAlex for { <https://semopenalex.org/work/W3177029382> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3177029382 endingPage "4211" @default.
- W3177029382 startingPage "4211" @default.
- W3177029382 abstract "Shape classification and segmentation of point cloud data are two of the most demanding tasks in photogrammetry and remote sensing applications, which aim to recognize object categories or point labels. Point convolution is an essential operation when designing a network on point clouds for these tasks, which helps to explore 3D local points for feature learning. In this paper, we propose a novel point convolution (PSConv) using separable weights learned with polynomials for 3D point cloud analysis. Specifically, we generalize the traditional convolution defined on the regular data to a 3D point cloud by learning the point convolution kernels based on the polynomials of transformed local point coordinates. We further propose a separable assumption on the convolution kernels to reduce the parameter size and computational cost for our point convolution. Using this novel point convolution, a hierarchical network (PSNet) defined on the point cloud is proposed for 3D shape analysis tasks such as 3D shape classification and segmentation. Experiments are conducted on standard datasets, including synthetic and real scanned ones, and our PSNet achieves state-of-the-art accuracies for shape classification, as well as competitive results for shape segmentation compared with previous methods." @default.
- W3177029382 created "2021-07-05" @default.
- W3177029382 creator A5037419606 @default.
- W3177029382 creator A5053510040 @default.
- W3177029382 date "2021-06-19" @default.
- W3177029382 modified "2023-09-26" @default.
- W3177029382 title "Learning Polynomial-Based Separable Convolution for 3D Point Cloud Analysis" @default.
- W3177029382 cites W1984772269 @default.
- W3177029382 cites W2105464873 @default.
- W3177029382 cites W2553307952 @default.
- W3177029382 cites W2558580397 @default.
- W3177029382 cites W2810240468 @default.
- W3177029382 cites W2979750740 @default.
- W3177029382 doi "https://doi.org/10.3390/s21124211" @default.
- W3177029382 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8235014" @default.
- W3177029382 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34205310" @default.
- W3177029382 hasPublicationYear "2021" @default.
- W3177029382 type Work @default.
- W3177029382 sameAs 3177029382 @default.
- W3177029382 citedByCount "0" @default.
- W3177029382 crossrefType "journal-article" @default.
- W3177029382 hasAuthorship W3177029382A5037419606 @default.
- W3177029382 hasAuthorship W3177029382A5053510040 @default.
- W3177029382 hasBestOaLocation W31770293821 @default.
- W3177029382 hasConcept C11413529 @default.
- W3177029382 hasConcept C131979681 @default.
- W3177029382 hasConcept C134306372 @default.
- W3177029382 hasConcept C138885662 @default.
- W3177029382 hasConcept C153180895 @default.
- W3177029382 hasConcept C154945302 @default.
- W3177029382 hasConcept C2524010 @default.
- W3177029382 hasConcept C2776401178 @default.
- W3177029382 hasConcept C28719098 @default.
- W3177029382 hasConcept C31972630 @default.
- W3177029382 hasConcept C33923547 @default.
- W3177029382 hasConcept C41008148 @default.
- W3177029382 hasConcept C41895202 @default.
- W3177029382 hasConcept C45347329 @default.
- W3177029382 hasConcept C50644808 @default.
- W3177029382 hasConcept C70710897 @default.
- W3177029382 hasConcept C89600930 @default.
- W3177029382 hasConcept C90119067 @default.
- W3177029382 hasConceptScore W3177029382C11413529 @default.
- W3177029382 hasConceptScore W3177029382C131979681 @default.
- W3177029382 hasConceptScore W3177029382C134306372 @default.
- W3177029382 hasConceptScore W3177029382C138885662 @default.
- W3177029382 hasConceptScore W3177029382C153180895 @default.
- W3177029382 hasConceptScore W3177029382C154945302 @default.
- W3177029382 hasConceptScore W3177029382C2524010 @default.
- W3177029382 hasConceptScore W3177029382C2776401178 @default.
- W3177029382 hasConceptScore W3177029382C28719098 @default.
- W3177029382 hasConceptScore W3177029382C31972630 @default.
- W3177029382 hasConceptScore W3177029382C33923547 @default.
- W3177029382 hasConceptScore W3177029382C41008148 @default.
- W3177029382 hasConceptScore W3177029382C41895202 @default.
- W3177029382 hasConceptScore W3177029382C45347329 @default.
- W3177029382 hasConceptScore W3177029382C50644808 @default.
- W3177029382 hasConceptScore W3177029382C70710897 @default.
- W3177029382 hasConceptScore W3177029382C89600930 @default.
- W3177029382 hasConceptScore W3177029382C90119067 @default.
- W3177029382 hasFunder F4320321001 @default.
- W3177029382 hasIssue "12" @default.
- W3177029382 hasLocation W31770293821 @default.
- W3177029382 hasLocation W31770293822 @default.
- W3177029382 hasOpenAccess W3177029382 @default.
- W3177029382 hasPrimaryLocation W31770293821 @default.
- W3177029382 hasRelatedWork W1669643531 @default.
- W3177029382 hasRelatedWork W2005437358 @default.
- W3177029382 hasRelatedWork W2008656436 @default.
- W3177029382 hasRelatedWork W2039154422 @default.
- W3177029382 hasRelatedWork W2122581818 @default.
- W3177029382 hasRelatedWork W2517104666 @default.
- W3177029382 hasRelatedWork W2556085923 @default.
- W3177029382 hasRelatedWork W2929240682 @default.
- W3177029382 hasRelatedWork W4310007291 @default.
- W3177029382 hasRelatedWork W2182382398 @default.
- W3177029382 hasVolume "21" @default.
- W3177029382 isParatext "false" @default.
- W3177029382 isRetracted "false" @default.
- W3177029382 magId "3177029382" @default.
- W3177029382 workType "article" @default.