FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891396148> ?p ?o ?g. }

• W2891396148 endingPage "12" @default.
• W2891396148 startingPage "1" @default.
• W2891396148 abstract "Polygonal meshes provide an efficient representation for 3D shapes. They explicitly capture both shape surface and topology, and leverage non-uniformity to represent large flat regions as well as sharp, intricate features. This non-uniformity and irregularity, however, inhibits mesh analysis efforts using neural networks that combine convolution and pooling operations. In this paper, we utilize the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes. Analogous to classic CNNs, MeshCNN combines specialized convolution and pooling layers that operate on the mesh edges, by leveraging their intrinsic geodesic connections. Convolutions are applied on edges and the four edges of their incident triangles, and pooling is applied via an edge collapse operation that retains surface topology, thereby, generating new mesh connectivity for the subsequent convolutions. MeshCNN learns which edges to collapse, thus forming a task-driven process where the network exposes and expands the important features while discarding the redundant ones. We demonstrate the effectiveness of our task-driven pooling on various learning tasks applied to 3D meshes." @default.
• W2891396148 created "2018-09-27" @default.
• W2891396148 creator A5008327409 @default.
• W2891396148 creator A5009881746 @default.
• W2891396148 creator A5036688260 @default.
• W2891396148 creator A5041744005 @default.
• W2891396148 creator A5042130063 @default.
• W2891396148 creator A5072571599 @default.
• W2891396148 date "2019-07-12" @default.
• W2891396148 modified "2023-10-14" @default.
• W2891396148 title "MeshCNN" @default.
• W2891396148 cites W104211377 @default.
• W2891396148 cites W1644641054 @default.
• W2891396148 cites W1798731418 @default.
• W2891396148 cites W1901129140 @default.
• W2891396148 cites W1920022804 @default.
• W2891396148 cites W1985907520 @default.
• W2891396148 cites W1996187920 @default.
• W2891396148 cites W2003940193 @default.
• W2891396148 cites W2036163530 @default.
• W2891396148 cites W2052789583 @default.
• W2891396148 cites W2106723645 @default.
• W2891396148 cites W2113634802 @default.
• W2891396148 cites W2122578066 @default.
• W2891396148 cites W2235901111 @default.
• W2891396148 cites W2518780089 @default.
• W2891396148 cites W2558460151 @default.
• W2891396148 cites W2558748708 @default.
• W2891396148 cites W2594083602 @default.
• W2891396148 cites W2728183739 @default.
• W2891396148 cites W2734558172 @default.
• W2891396148 cites W2737081152 @default.
• W2891396148 cites W2768294793 @default.
• W2891396148 cites W2780485466 @default.
• W2891396148 cites W2791092480 @default.
• W2891396148 cites W2797997528 @default.
• W2891396148 cites W2884345717 @default.
• W2891396148 cites W2913772345 @default.
• W2891396148 cites W2963021451 @default.
• W2891396148 cites W2963109677 @default.
• W2891396148 cites W2963197375 @default.
• W2891396148 cites W2963226018 @default.
• W2891396148 cites W2963333168 @default.
• W2891396148 cites W2963557767 @default.
• W2891396148 cites W2963991385 @default.
• W2891396148 cites W2964253930 @default.
• W2891396148 cites W3104141662 @default.
• W2891396148 cites W4236667477 @default.
• W2891396148 doi "https://doi.org/10.1145/3306346.3322959" @default.
• W2891396148 hasPublicationYear "2019" @default.
• W2891396148 type Work @default.
• W2891396148 sameAs 2891396148 @default.
• W2891396148 citedByCount "291" @default.
• W2891396148 countsByYear W28913961482019 @default.
• W2891396148 countsByYear W28913961482020 @default.
• W2891396148 countsByYear W28913961482021 @default.
• W2891396148 countsByYear W28913961482022 @default.
• W2891396148 countsByYear W28913961482023 @default.
• W2891396148 crossrefType "journal-article" @default.
• W2891396148 hasAuthorship W2891396148A5008327409 @default.
• W2891396148 hasAuthorship W2891396148A5009881746 @default.
• W2891396148 hasAuthorship W2891396148A5036688260 @default.
• W2891396148 hasAuthorship W2891396148A5041744005 @default.
• W2891396148 hasAuthorship W2891396148A5042130063 @default.
• W2891396148 hasAuthorship W2891396148A5072571599 @default.
• W2891396148 hasBestOaLocation W28913961482 @default.
• W2891396148 hasConcept C11413529 @default.
• W2891396148 hasConcept C114614502 @default.
• W2891396148 hasConcept C121684516 @default.
• W2891396148 hasConcept C153083717 @default.
• W2891396148 hasConcept C154945302 @default.
• W2891396148 hasConcept C162307627 @default.
• W2891396148 hasConcept C165818556 @default.
• W2891396148 hasConcept C17744445 @default.
• W2891396148 hasConcept C184720557 @default.
• W2891396148 hasConcept C199539241 @default.
• W2891396148 hasConcept C2524010 @default.
• W2891396148 hasConcept C2776359362 @default.
• W2891396148 hasConcept C31487907 @default.
• W2891396148 hasConcept C33923547 @default.
• W2891396148 hasConcept C41008148 @default.
• W2891396148 hasConcept C45347329 @default.
• W2891396148 hasConcept C50644808 @default.
• W2891396148 hasConcept C70437156 @default.
• W2891396148 hasConcept C80444323 @default.
• W2891396148 hasConcept C81363708 @default.
• W2891396148 hasConcept C94625758 @default.
• W2891396148 hasConceptScore W2891396148C11413529 @default.
• W2891396148 hasConceptScore W2891396148C114614502 @default.
• W2891396148 hasConceptScore W2891396148C121684516 @default.
• W2891396148 hasConceptScore W2891396148C153083717 @default.
• W2891396148 hasConceptScore W2891396148C154945302 @default.
• W2891396148 hasConceptScore W2891396148C162307627 @default.
• W2891396148 hasConceptScore W2891396148C165818556 @default.
• W2891396148 hasConceptScore W2891396148C17744445 @default.
• W2891396148 hasConceptScore W2891396148C184720557 @default.
• W2891396148 hasConceptScore W2891396148C199539241 @default.
• W2891396148 hasConceptScore W2891396148C2524010 @default.

• next