Matches in SemOpenAlex for { <https://semopenalex.org/work/W3177138220> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3177138220 abstract "This paper presents new designs of graph convolutional neural networks (GCNs) on 3D meshes for 3D object segmentation and classification. We use the faces of the mesh as basic processing units and represent a 3D mesh as a graph where each node corresponds to a face. To enhance the descriptive power of the graph, we introduce a 1-ring face neighbourhood structure to derive novel multi-dimensional spatial and structure features to represent the graph nodes. Based on this new graph representation, we then design a densely connected graph convolutional block which aggregates local and regional features as the key construction component to build effective and efficient practical GCN models for 3D object classification and segmentation. We will present experimental results to show that our new technique outperforms state of the art where our models are shown to have the smallest number of parameters and consietently achieve the highest accuracies across a number of benchmark datasets. We will also present ablation studies to demonstrate the soundness of our design principles and the effectiveness of our practical models." @default.
- W3177138220 created "2021-07-05" @default.
- W3177138220 creator A5036351852 @default.
- W3177138220 date "2021-06-30" @default.
- W3177138220 modified "2023-09-27" @default.
- W3177138220 title "Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification" @default.
- W3177138220 cites W1026270304 @default.
- W3177138220 cites W1522301498 @default.
- W3177138220 cites W1644641054 @default.
- W3177138220 cites W1662382123 @default.
- W3177138220 cites W1861492603 @default.
- W3177138220 cites W1920022804 @default.
- W3177138220 cites W1985907520 @default.
- W3177138220 cites W1989191365 @default.
- W3177138220 cites W1996187920 @default.
- W3177138220 cites W2003940193 @default.
- W3177138220 cites W2036163530 @default.
- W3177138220 cites W2122578066 @default.
- W3177138220 cites W2138911744 @default.
- W3177138220 cites W2194775991 @default.
- W3177138220 cites W2331143823 @default.
- W3177138220 cites W2408279554 @default.
- W3177138220 cites W2518780089 @default.
- W3177138220 cites W2519887557 @default.
- W3177138220 cites W2560609797 @default.
- W3177138220 cites W2672952450 @default.
- W3177138220 cites W2728183739 @default.
- W3177138220 cites W2737081152 @default.
- W3177138220 cites W2751808960 @default.
- W3177138220 cites W2758922793 @default.
- W3177138220 cites W2791092480 @default.
- W3177138220 cites W2798895698 @default.
- W3177138220 cites W2804057010 @default.
- W3177138220 cites W2810641456 @default.
- W3177138220 cites W2898360221 @default.
- W3177138220 cites W2908527700 @default.
- W3177138220 cites W2930709109 @default.
- W3177138220 cites W2951309718 @default.
- W3177138220 cites W2963021451 @default.
- W3177138220 cites W2963121255 @default.
- W3177138220 cites W2963197375 @default.
- W3177138220 cites W2963446712 @default.
- W3177138220 cites W2963991385 @default.
- W3177138220 cites W2964051675 @default.
- W3177138220 cites W2979750740 @default.
- W3177138220 cites W2981532110 @default.
- W3177138220 cites W2990045899 @default.
- W3177138220 cites W3035541121 @default.
- W3177138220 cites W3069968251 @default.
- W3177138220 hasPublicationYear "2021" @default.
- W3177138220 type Work @default.
- W3177138220 sameAs 3177138220 @default.
- W3177138220 citedByCount "0" @default.
- W3177138220 crossrefType "posted-content" @default.
- W3177138220 hasAuthorship W3177138220A5036351852 @default.
- W3177138220 hasConcept C121684516 @default.
- W3177138220 hasConcept C132525143 @default.
- W3177138220 hasConcept C153180895 @default.
- W3177138220 hasConcept C154945302 @default.
- W3177138220 hasConcept C31487907 @default.
- W3177138220 hasConcept C41008148 @default.
- W3177138220 hasConcept C80444323 @default.
- W3177138220 hasConcept C81363708 @default.
- W3177138220 hasConcept C89600930 @default.
- W3177138220 hasConceptScore W3177138220C121684516 @default.
- W3177138220 hasConceptScore W3177138220C132525143 @default.
- W3177138220 hasConceptScore W3177138220C153180895 @default.
- W3177138220 hasConceptScore W3177138220C154945302 @default.
- W3177138220 hasConceptScore W3177138220C31487907 @default.
- W3177138220 hasConceptScore W3177138220C41008148 @default.
- W3177138220 hasConceptScore W3177138220C80444323 @default.
- W3177138220 hasConceptScore W3177138220C81363708 @default.
- W3177138220 hasConceptScore W3177138220C89600930 @default.
- W3177138220 hasLocation W31771382201 @default.
- W3177138220 hasOpenAccess W3177138220 @default.
- W3177138220 hasPrimaryLocation W31771382201 @default.
- W3177138220 hasRelatedWork W2758922793 @default.
- W3177138220 hasRelatedWork W2784055555 @default.
- W3177138220 hasRelatedWork W2805090752 @default.
- W3177138220 hasRelatedWork W2891082150 @default.
- W3177138220 hasRelatedWork W2907221513 @default.
- W3177138220 hasRelatedWork W2913355189 @default.
- W3177138220 hasRelatedWork W2915738933 @default.
- W3177138220 hasRelatedWork W2952832237 @default.
- W3177138220 hasRelatedWork W2970672451 @default.
- W3177138220 hasRelatedWork W2972933289 @default.
- W3177138220 hasRelatedWork W2991003211 @default.
- W3177138220 hasRelatedWork W2998423439 @default.
- W3177138220 hasRelatedWork W3028917156 @default.
- W3177138220 hasRelatedWork W3045020488 @default.
- W3177138220 hasRelatedWork W3091978167 @default.
- W3177138220 hasRelatedWork W3095213891 @default.
- W3177138220 hasRelatedWork W3123559604 @default.
- W3177138220 hasRelatedWork W3195439460 @default.
- W3177138220 hasRelatedWork W3199900475 @default.
- W3177138220 hasRelatedWork W3205147687 @default.
- W3177138220 isParatext "false" @default.
- W3177138220 isRetracted "false" @default.
- W3177138220 magId "3177138220" @default.
- W3177138220 workType "article" @default.