FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387503861> ?p ?o ?g. }

• W4387503861 endingPage "103629" @default.
• W4387503861 startingPage "103629" @default.
• W4387503861 abstract "Geometry understanding is a core concept of computer-aided design and engineering (CAD/CAE). Deep neural networks have increasingly shown success as a method of processing complex inputs to achieve abstract tasks. This work revisits a generic and relatively simple approach to 3D deep learning - a point-based graph neural network - and develops best-practices and modifications to alleviate traditional drawbacks. It is shown that these methods should not be discounted for CAD tasks; with proper implementation, they can be competitive with more specifically designed approaches. Through an additive study, this work investigates how the boundary representation data can be fully utilised by leveraging the flexibility of point-based graph networks. The final configuration significantly improves on the predictive accuracy of a standard PointNet++ network across multiple CAD model segmentation datasets and achieves state-of-the-art performance on the MFCAD++ machining features dataset. The proposed modifications leave the core neural network unchanged and results also suggest that they can be applied to other point-based approaches." @default.
• W4387503861 created "2023-10-11" @default.
• W4387503861 creator A5002229225 @default.
• W4387503861 creator A5008774991 @default.
• W4387503861 creator A5011334040 @default.
• W4387503861 creator A5038981025 @default.
• W4387503861 creator A5090857360 @default.
• W4387503861 creator A5093037424 @default.
• W4387503861 date "2023-10-01" @default.
• W4387503861 modified "2023-10-18" @default.
• W4387503861 title "Extending Point-Based Deep Learning Approaches for Better Semantic Segmentation in CAD" @default.
• W4387503861 cites W1490682695 @default.
• W4387503861 cites W1644641054 @default.
• W4387503861 cites W1901129140 @default.
• W4387503861 cites W1969014399 @default.
• W4387503861 cites W1995870875 @default.
• W4387503861 cites W2079563222 @default.
• W4387503861 cites W2082724578 @default.
• W4387503861 cites W2366389387 @default.
• W4387503861 cites W2553307952 @default.
• W4387503861 cites W2563408008 @default.
• W4387503861 cites W2797161036 @default.
• W4387503861 cites W2797813920 @default.
• W4387503861 cites W2891396148 @default.
• W4387503861 cites W2909281404 @default.
• W4387503861 cites W2919115771 @default.
• W4387503861 cites W2963021451 @default.
• W4387503861 cites W2963035165 @default.
• W4387503861 cites W2963150697 @default.
• W4387503861 cites W2963158438 @default.
• W4387503861 cites W2963509914 @default.
• W4387503861 cites W2963991385 @default.
• W4387503861 cites W2979750740 @default.
• W4387503861 cites W2990613095 @default.
• W4387503861 cites W3002505517 @default.
• W4387503861 cites W3129530645 @default.
• W4387503861 cites W3173520058 @default.
• W4387503861 cites W3174904509 @default.
• W4387503861 cites W4210581468 @default.
• W4387503861 cites W4210906714 @default.
• W4387503861 cites W4212966960 @default.
• W4387503861 cites W4214755140 @default.
• W4387503861 cites W4229063534 @default.
• W4387503861 cites W4250950338 @default.
• W4387503861 cites W4288734997 @default.
• W4387503861 cites W4312443924 @default.
• W4387503861 doi "https://doi.org/10.1016/j.cad.2023.103629" @default.
• W4387503861 hasPublicationYear "2023" @default.
• W4387503861 type Work @default.
• W4387503861 citedByCount "0" @default.
• W4387503861 crossrefType "journal-article" @default.
• W4387503861 hasAuthorship W4387503861A5002229225 @default.
• W4387503861 hasAuthorship W4387503861A5008774991 @default.
• W4387503861 hasAuthorship W4387503861A5011334040 @default.
• W4387503861 hasAuthorship W4387503861A5038981025 @default.
• W4387503861 hasAuthorship W4387503861A5090857360 @default.
• W4387503861 hasAuthorship W4387503861A5093037424 @default.
• W4387503861 hasBestOaLocation W43875038611 @default.
• W4387503861 hasConcept C105795698 @default.
• W4387503861 hasConcept C108583219 @default.
• W4387503861 hasConcept C111919701 @default.
• W4387503861 hasConcept C117258860 @default.
• W4387503861 hasConcept C119823426 @default.
• W4387503861 hasConcept C119857082 @default.
• W4387503861 hasConcept C124101348 @default.
• W4387503861 hasConcept C127413603 @default.
• W4387503861 hasConcept C132525143 @default.
• W4387503861 hasConcept C134306372 @default.
• W4387503861 hasConcept C154945302 @default.
• W4387503861 hasConcept C17744445 @default.
• W4387503861 hasConcept C194789388 @default.
• W4387503861 hasConcept C199539241 @default.
• W4387503861 hasConcept C199639397 @default.
• W4387503861 hasConcept C2524010 @default.
• W4387503861 hasConcept C2776359362 @default.
• W4387503861 hasConcept C2780598303 @default.
• W4387503861 hasConcept C28719098 @default.
• W4387503861 hasConcept C33923547 @default.
• W4387503861 hasConcept C41008148 @default.
• W4387503861 hasConcept C50644808 @default.
• W4387503861 hasConcept C62354387 @default.
• W4387503861 hasConcept C80444323 @default.
• W4387503861 hasConcept C89600930 @default.
• W4387503861 hasConcept C94625758 @default.
• W4387503861 hasConceptScore W4387503861C105795698 @default.
• W4387503861 hasConceptScore W4387503861C108583219 @default.
• W4387503861 hasConceptScore W4387503861C111919701 @default.
• W4387503861 hasConceptScore W4387503861C117258860 @default.
• W4387503861 hasConceptScore W4387503861C119823426 @default.
• W4387503861 hasConceptScore W4387503861C119857082 @default.
• W4387503861 hasConceptScore W4387503861C124101348 @default.
• W4387503861 hasConceptScore W4387503861C127413603 @default.
• W4387503861 hasConceptScore W4387503861C132525143 @default.
• W4387503861 hasConceptScore W4387503861C134306372 @default.
• W4387503861 hasConceptScore W4387503861C154945302 @default.
• W4387503861 hasConceptScore W4387503861C17744445 @default.
• W4387503861 hasConceptScore W4387503861C194789388 @default.
• W4387503861 hasConceptScore W4387503861C199539241 @default.

• next