Matches in SemOpenAlex for { <https://semopenalex.org/work/W2801933800> ?p ?o ?g. }
- W2801933800 abstract "Depth sensors used in autonomous driving and gaming systems often report back 3D point clouds. The lack of structure from these sensors does not allow these systems to take advantage of recent advances in convolutional neural networks which are dependent upon traditional filtering and pooling operations. Analogous to image based convolutional architectures, recently introduced graph based architectures afford similar filtering and pooling operations on arbitrary graphs. We adopt these graph based methods to 3D point clouds to introduce a generic vector representation of 3D graphs, we call graph 3D (G3D). We believe we are the first to use large scale transfer learning on 3D point cloud data and demonstrate the discriminant power of our salient latent representation of 3D point clouds on unforeseen test sets. By using our G3D network (G3DNet) as a feature extractor, and then pairing G3D feature vectors with a standard classifier, we achieve the best accuracy on ModelNet10 (93.1%) and ModelNet 40 (91.7%) for a graph network, and comparable performance on the Sydney Urban Objects dataset to other methods. This general-purpose feature extractor can be used as an off-the-shelf component in other 3D scene understanding or object tracking works." @default.
- W2801933800 created "2018-05-17" @default.
- W2801933800 creator A5002928269 @default.
- W2801933800 creator A5019474403 @default.
- W2801933800 creator A5030830109 @default.
- W2801933800 creator A5032475867 @default.
- W2801933800 creator A5070182094 @default.
- W2801933800 creator A5089506619 @default.
- W2801933800 date "2018-03-01" @default.
- W2801933800 modified "2023-10-02" @default.
- W2801933800 title "General-Purpose Deep Point Cloud Feature Extractor" @default.
- W2801933800 cites W1522734439 @default.
- W2801933800 cites W1629010235 @default.
- W2801933800 cites W1644641054 @default.
- W2801933800 cites W1905882502 @default.
- W2801933800 cites W1920022804 @default.
- W2801933800 cites W1947481528 @default.
- W2801933800 cites W1991252559 @default.
- W2801933800 cites W2029041800 @default.
- W2801933800 cites W2108598243 @default.
- W2801933800 cites W2117539524 @default.
- W2801933800 cites W2132914434 @default.
- W2801933800 cites W2139501017 @default.
- W2801933800 cites W2145131285 @default.
- W2801933800 cites W2208045473 @default.
- W2801933800 cites W2211722331 @default.
- W2801933800 cites W2342223463 @default.
- W2801933800 cites W2520377600 @default.
- W2801933800 cites W2592023181 @default.
- W2801933800 cites W2594083602 @default.
- W2801933800 cites W2606202972 @default.
- W2801933800 cites W2734558172 @default.
- W2801933800 cites W2738835886 @default.
- W2801933800 cites W2758922793 @default.
- W2801933800 cites W2794206172 @default.
- W2801933800 cites W2962724911 @default.
- W2801933800 cites W2962928871 @default.
- W2801933800 cites W2963333168 @default.
- W2801933800 cites W3104097132 @default.
- W2801933800 doi "https://doi.org/10.1109/wacv.2018.00218" @default.
- W2801933800 hasPublicationYear "2018" @default.
- W2801933800 type Work @default.
- W2801933800 sameAs 2801933800 @default.
- W2801933800 citedByCount "27" @default.
- W2801933800 countsByYear W28019338002018 @default.
- W2801933800 countsByYear W28019338002019 @default.
- W2801933800 countsByYear W28019338002020 @default.
- W2801933800 countsByYear W28019338002021 @default.
- W2801933800 countsByYear W28019338002022 @default.
- W2801933800 countsByYear W28019338002023 @default.
- W2801933800 crossrefType "proceedings-article" @default.
- W2801933800 hasAuthorship W2801933800A5002928269 @default.
- W2801933800 hasAuthorship W2801933800A5019474403 @default.
- W2801933800 hasAuthorship W2801933800A5030830109 @default.
- W2801933800 hasAuthorship W2801933800A5032475867 @default.
- W2801933800 hasAuthorship W2801933800A5070182094 @default.
- W2801933800 hasAuthorship W2801933800A5089506619 @default.
- W2801933800 hasConcept C124101348 @default.
- W2801933800 hasConcept C131979681 @default.
- W2801933800 hasConcept C132525143 @default.
- W2801933800 hasConcept C138885662 @default.
- W2801933800 hasConcept C153180895 @default.
- W2801933800 hasConcept C154945302 @default.
- W2801933800 hasConcept C2776401178 @default.
- W2801933800 hasConcept C31972630 @default.
- W2801933800 hasConcept C41008148 @default.
- W2801933800 hasConcept C41895202 @default.
- W2801933800 hasConcept C52622490 @default.
- W2801933800 hasConcept C70437156 @default.
- W2801933800 hasConcept C80444323 @default.
- W2801933800 hasConcept C81363708 @default.
- W2801933800 hasConcept C95623464 @default.
- W2801933800 hasConceptScore W2801933800C124101348 @default.
- W2801933800 hasConceptScore W2801933800C131979681 @default.
- W2801933800 hasConceptScore W2801933800C132525143 @default.
- W2801933800 hasConceptScore W2801933800C138885662 @default.
- W2801933800 hasConceptScore W2801933800C153180895 @default.
- W2801933800 hasConceptScore W2801933800C154945302 @default.
- W2801933800 hasConceptScore W2801933800C2776401178 @default.
- W2801933800 hasConceptScore W2801933800C31972630 @default.
- W2801933800 hasConceptScore W2801933800C41008148 @default.
- W2801933800 hasConceptScore W2801933800C41895202 @default.
- W2801933800 hasConceptScore W2801933800C52622490 @default.
- W2801933800 hasConceptScore W2801933800C70437156 @default.
- W2801933800 hasConceptScore W2801933800C80444323 @default.
- W2801933800 hasConceptScore W2801933800C81363708 @default.
- W2801933800 hasConceptScore W2801933800C95623464 @default.
- W2801933800 hasLocation W28019338001 @default.
- W2801933800 hasOpenAccess W2801933800 @default.
- W2801933800 hasPrimaryLocation W28019338001 @default.
- W2801933800 hasRelatedWork W1504288058 @default.
- W2801933800 hasRelatedWork W2291847203 @default.
- W2801933800 hasRelatedWork W2319888919 @default.
- W2801933800 hasRelatedWork W2424871898 @default.
- W2801933800 hasRelatedWork W2517027266 @default.
- W2801933800 hasRelatedWork W2546942002 @default.
- W2801933800 hasRelatedWork W2979718872 @default.
- W2801933800 hasRelatedWork W3004532561 @default.
- W2801933800 hasRelatedWork W3158534694 @default.
- W2801933800 hasRelatedWork W4225852842 @default.