Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201750968> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3201750968 abstract "In recent years, convolutional neural networks on point clouds have greatly improved the performance of point cloud classification and segmentation. However, the irregularity and disorder of point clouds make the convolution operation ill-suited to preserve the spatial-local structure and make the existing convolution networks very shallow. In order to solve the problems, we propose a novel pre-processor network named KeypointNet which ranks the point cloud according to the contribution to the final task, such as classification and segmentation. With the ordered point cloud, a convolution neural network on point clouds goes as deeper as possible similar to that on images. Two scoring mechanisms: directly scoring (DS) and gradually scoring (GS), are designed based on a pre-trained PointNet which is easily and fast trained. Both scoring mechanisms score a point depending on its contribution to the output of PointNet. The former scores the point cloud only one time and the later scores the point cloud on grade level. KeypointNet can be unified with any existing convolution neural networks on point clouds. Extensive experiments demonstrate that our method is effective and efficient and achieves SOTA classification results and comparable segmentation results, while greatly reducing space consumption." @default.
- W3201750968 created "2021-10-11" @default.
- W3201750968 creator A5030144058 @default.
- W3201750968 creator A5031701188 @default.
- W3201750968 creator A5076485255 @default.
- W3201750968 date "2021-01-01" @default.
- W3201750968 modified "2023-09-23" @default.
- W3201750968 title "KeypointNet: Ranking Point Cloud for Convolution Neural Network" @default.
- W3201750968 cites W2556802233 @default.
- W3201750968 cites W2795374598 @default.
- W3201750968 cites W2798270772 @default.
- W3201750968 cites W2810240468 @default.
- W3201750968 cites W2913483530 @default.
- W3201750968 cites W2962887844 @default.
- W3201750968 cites W2962889053 @default.
- W3201750968 cites W2962928871 @default.
- W3201750968 cites W2963053547 @default.
- W3201750968 cites W2963123724 @default.
- W3201750968 cites W2963158438 @default.
- W3201750968 cites W2963231572 @default.
- W3201750968 cites W2963530975 @default.
- W3201750968 cites W2963719584 @default.
- W3201750968 cites W2964060890 @default.
- W3201750968 cites W2964062501 @default.
- W3201750968 cites W2964161804 @default.
- W3201750968 cites W2979750740 @default.
- W3201750968 cites W2981440248 @default.
- W3201750968 cites W2981983525 @default.
- W3201750968 cites W2982210492 @default.
- W3201750968 cites W2990613095 @default.
- W3201750968 cites W3034664537 @default.
- W3201750968 doi "https://doi.org/10.1007/978-3-030-87361-5_10" @default.
- W3201750968 hasPublicationYear "2021" @default.
- W3201750968 type Work @default.
- W3201750968 sameAs 3201750968 @default.
- W3201750968 citedByCount "0" @default.
- W3201750968 crossrefType "book-chapter" @default.
- W3201750968 hasAuthorship W3201750968A5030144058 @default.
- W3201750968 hasAuthorship W3201750968A5031701188 @default.
- W3201750968 hasAuthorship W3201750968A5076485255 @default.
- W3201750968 hasConcept C131979681 @default.
- W3201750968 hasConcept C153180895 @default.
- W3201750968 hasConcept C154945302 @default.
- W3201750968 hasConcept C189430467 @default.
- W3201750968 hasConcept C2524010 @default.
- W3201750968 hasConcept C28719098 @default.
- W3201750968 hasConcept C33923547 @default.
- W3201750968 hasConcept C41008148 @default.
- W3201750968 hasConcept C45347329 @default.
- W3201750968 hasConcept C50644808 @default.
- W3201750968 hasConcept C81363708 @default.
- W3201750968 hasConcept C89600930 @default.
- W3201750968 hasConceptScore W3201750968C131979681 @default.
- W3201750968 hasConceptScore W3201750968C153180895 @default.
- W3201750968 hasConceptScore W3201750968C154945302 @default.
- W3201750968 hasConceptScore W3201750968C189430467 @default.
- W3201750968 hasConceptScore W3201750968C2524010 @default.
- W3201750968 hasConceptScore W3201750968C28719098 @default.
- W3201750968 hasConceptScore W3201750968C33923547 @default.
- W3201750968 hasConceptScore W3201750968C41008148 @default.
- W3201750968 hasConceptScore W3201750968C45347329 @default.
- W3201750968 hasConceptScore W3201750968C50644808 @default.
- W3201750968 hasConceptScore W3201750968C81363708 @default.
- W3201750968 hasConceptScore W3201750968C89600930 @default.
- W3201750968 hasLocation W32017509681 @default.
- W3201750968 hasOpenAccess W3201750968 @default.
- W3201750968 hasPrimaryLocation W32017509681 @default.
- W3201750968 hasRelatedWork W10575013 @default.
- W3201750968 hasRelatedWork W14128562 @default.
- W3201750968 hasRelatedWork W14587445 @default.
- W3201750968 hasRelatedWork W2366400 @default.
- W3201750968 hasRelatedWork W274842 @default.
- W3201750968 hasRelatedWork W2893967 @default.
- W3201750968 hasRelatedWork W4771408 @default.
- W3201750968 hasRelatedWork W6368054 @default.
- W3201750968 hasRelatedWork W9190101 @default.
- W3201750968 hasRelatedWork W13673164 @default.
- W3201750968 isParatext "false" @default.
- W3201750968 isRetracted "false" @default.
- W3201750968 magId "3201750968" @default.
- W3201750968 workType "book-chapter" @default.