Matches in SemOpenAlex for { <https://semopenalex.org/work/W4353075192> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4353075192 endingPage "171" @default.
- W4353075192 startingPage "171" @default.
- W4353075192 abstract "3D mesh as a complex data structure can provide effective shape representation for 3D objects, but due to the irregularity and disorder of the mesh data, it is difficult for convolutional neural networks to be directly applied to 3D mesh data processing. At the same time, the extensive use of convolutional kernels and pooling layers focusing on local features can cause the loss of spatial information and dependencies of low-level features. In this paper, we propose a self-attentive convolutional network MixFormer applied to 3D mesh models. By defining 3D convolutional kernels and vector self-attention mechanisms applicable to 3D mesh models, our neural network is able to learn 3D mesh model features. Combining the features of convolutional networks and transformer networks, the network can focus on both local detail features and long-range dependencies between features, thus achieving good learning results without stacking multiple layers and saving arithmetic overhead compared to pure transformer architectures. We conduct classification and semantic segmentation experiments on SHREC15, SCAPE, FAUST, MIT, and Adobe Fuse datasets. Experimental results show that the network can achieve 96.7% classification and better segmentation results by using fewer parameters and network layers." @default.
- W4353075192 created "2023-03-23" @default.
- W4353075192 creator A5019265388 @default.
- W4353075192 creator A5052676364 @default.
- W4353075192 creator A5066282713 @default.
- W4353075192 date "2023-03-21" @default.
- W4353075192 modified "2023-09-30" @default.
- W4353075192 title "MixFormer: A Self-Attentive Convolutional Network for 3D Mesh Object Recognition" @default.
- W4353075192 cites W1507506748 @default.
- W4353075192 cites W2031489346 @default.
- W4353075192 cites W2102605133 @default.
- W4353075192 cites W2117287331 @default.
- W4353075192 cites W2194775991 @default.
- W4353075192 cites W2216125271 @default.
- W4353075192 cites W2252738564 @default.
- W4353075192 cites W2549139847 @default.
- W4353075192 cites W2618530766 @default.
- W4353075192 cites W2737081152 @default.
- W4353075192 cites W2780485466 @default.
- W4353075192 cites W2963150697 @default.
- W4353075192 cites W2964080601 @default.
- W4353075192 cites W2990026901 @default.
- W4353075192 cites W3016719260 @default.
- W4353075192 cites W3034885317 @default.
- W4353075192 cites W3039448353 @default.
- W4353075192 cites W3097065222 @default.
- W4353075192 cites W3109462203 @default.
- W4353075192 cites W3112647050 @default.
- W4353075192 cites W3138516171 @default.
- W4353075192 cites W3153465022 @default.
- W4353075192 cites W3170953943 @default.
- W4353075192 cites W3175199633 @default.
- W4353075192 cites W3178544809 @default.
- W4353075192 cites W4214755140 @default.
- W4353075192 cites W4224233602 @default.
- W4353075192 cites W4226401017 @default.
- W4353075192 cites W4231059779 @default.
- W4353075192 cites W4292793978 @default.
- W4353075192 cites W4292794070 @default.
- W4353075192 cites W4312446817 @default.
- W4353075192 cites W639708223 @default.
- W4353075192 doi "https://doi.org/10.3390/a16030171" @default.
- W4353075192 hasPublicationYear "2023" @default.
- W4353075192 type Work @default.
- W4353075192 citedByCount "0" @default.
- W4353075192 crossrefType "journal-article" @default.
- W4353075192 hasAuthorship W4353075192A5019265388 @default.
- W4353075192 hasAuthorship W4353075192A5052676364 @default.
- W4353075192 hasAuthorship W4353075192A5066282713 @default.
- W4353075192 hasBestOaLocation W43530751921 @default.
- W4353075192 hasConcept C121684516 @default.
- W4353075192 hasConcept C153180895 @default.
- W4353075192 hasConcept C154945302 @default.
- W4353075192 hasConcept C31487907 @default.
- W4353075192 hasConcept C41008148 @default.
- W4353075192 hasConcept C70437156 @default.
- W4353075192 hasConcept C81363708 @default.
- W4353075192 hasConcept C89600930 @default.
- W4353075192 hasConceptScore W4353075192C121684516 @default.
- W4353075192 hasConceptScore W4353075192C153180895 @default.
- W4353075192 hasConceptScore W4353075192C154945302 @default.
- W4353075192 hasConceptScore W4353075192C31487907 @default.
- W4353075192 hasConceptScore W4353075192C41008148 @default.
- W4353075192 hasConceptScore W4353075192C70437156 @default.
- W4353075192 hasConceptScore W4353075192C81363708 @default.
- W4353075192 hasConceptScore W4353075192C89600930 @default.
- W4353075192 hasIssue "3" @default.
- W4353075192 hasLocation W43530751921 @default.
- W4353075192 hasOpenAccess W4353075192 @default.
- W4353075192 hasPrimaryLocation W43530751921 @default.
- W4353075192 hasRelatedWork W2291847203 @default.
- W4353075192 hasRelatedWork W2424871898 @default.
- W4353075192 hasRelatedWork W2517027266 @default.
- W4353075192 hasRelatedWork W2756241593 @default.
- W4353075192 hasRelatedWork W2767651786 @default.
- W4353075192 hasRelatedWork W2912288872 @default.
- W4353075192 hasRelatedWork W2944724518 @default.
- W4353075192 hasRelatedWork W3004532561 @default.
- W4353075192 hasRelatedWork W4200528772 @default.
- W4353075192 hasRelatedWork W564581980 @default.
- W4353075192 hasVolume "16" @default.
- W4353075192 isParatext "false" @default.
- W4353075192 isRetracted "false" @default.
- W4353075192 workType "article" @default.