FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384282742> ?p ?o ?g. }

• W4384282742 endingPage "3246" @default.
• W4384282742 startingPage "3235" @default.
• W4384282742 abstract "Transformers have been widely applied in various vision tasks processing different data, such as images, videos and point clouds. However, the use of transformers in 3D mesh analysis remains largely unexplored. To address this gap, we propose a mesh transformer (MeT) that utilizes local self-attention on edges. MeT is based on a transformer layer that uses vector attention for edges, which is a kind of attention operator that supports adaptive modulation to both feature vectors and individual feature channels. Based on the transformer block, we build a lightweight mesh transformer network that consists of encoder and decoder. MeT provides general backbones for subsequent 3D mesh analysis tasks. To evaluate the effectiveness of our network MeT, we conduct experiments on two classic mesh analysis tasks: shape classification and shape segmentation. MeT achieves the state-of-the-art performance on multiple datasets for two tasks. We also conduct ablation studies to show the effectiveness of key designs in our network." @default.
• W4384282742 created "2023-07-15" @default.
• W4384282742 creator A5031008569 @default.
• W4384282742 creator A5037195768 @default.
• W4384282742 creator A5043757808 @default.
• W4384282742 creator A5050688373 @default.
• W4384282742 date "2023-07-14" @default.
• W4384282742 modified "2023-10-14" @default.
• W4384282742 title "MeT: mesh transformer with an edge" @default.
• W4384282742 cites W1901129140 @default.
• W4384282742 cites W1903029394 @default.
• W4384282742 cites W1905829557 @default.
• W4384282742 cites W1985907520 @default.
• W4384282742 cites W1996187920 @default.
• W4384282742 cites W2003940193 @default.
• W4384282742 cites W2102605133 @default.
• W4384282742 cites W2211722331 @default.
• W4384282742 cites W2556802233 @default.
• W4384282742 cites W2558460151 @default.
• W4384282742 cites W2618530766 @default.
• W4384282742 cites W2737081152 @default.
• W4384282742 cites W2780485466 @default.
• W4384282742 cites W2891396148 @default.
• W4384282742 cites W2902078856 @default.
• W4384282742 cites W2963021451 @default.
• W4384282742 cites W2968862542 @default.
• W4384282742 cites W3034885317 @default.
• W4384282742 cites W3035145671 @default.
• W4384282742 cites W3096609285 @default.
• W4384282742 cites W3101027576 @default.
• W4384282742 cites W3109462203 @default.
• W4384282742 cites W3138516171 @default.
• W4384282742 cites W3151130473 @default.
• W4384282742 cites W3153465022 @default.
• W4384282742 cites W3156072581 @default.
• W4384282742 cites W3159746229 @default.
• W4384282742 cites W3170953943 @default.
• W4384282742 cites W3175419759 @default.
• W4384282742 cites W3179709349 @default.
• W4384282742 cites W3180196270 @default.
• W4384282742 cites W3183434010 @default.
• W4384282742 cites W3203898101 @default.
• W4384282742 cites W3205353813 @default.
• W4384282742 cites W4210464928 @default.
• W4384282742 cites W4214612132 @default.
• W4384282742 cites W4214636423 @default.
• W4384282742 cites W4214755140 @default.
• W4384282742 cites W4214777292 @default.
• W4384282742 cites W4226401892 @default.
• W4384282742 cites W4236667477 @default.
• W4384282742 cites W4248870381 @default.
• W4384282742 cites W4306955484 @default.
• W4384282742 cites W4312270234 @default.
• W4384282742 cites W4312463544 @default.
• W4384282742 cites W4312788538 @default.
• W4384282742 cites W4313156423 @default.
• W4384282742 doi "https://doi.org/10.1007/s00371-023-02966-z" @default.
• W4384282742 hasPublicationYear "2023" @default.
• W4384282742 type Work @default.
• W4384282742 citedByCount "0" @default.
• W4384282742 crossrefType "journal-article" @default.
• W4384282742 hasAuthorship W4384282742A5031008569 @default.
• W4384282742 hasAuthorship W4384282742A5037195768 @default.
• W4384282742 hasAuthorship W4384282742A5043757808 @default.
• W4384282742 hasAuthorship W4384282742A5050688373 @default.
• W4384282742 hasBestOaLocation W43842827421 @default.
• W4384282742 hasConcept C119599485 @default.
• W4384282742 hasConcept C127413603 @default.
• W4384282742 hasConcept C153180895 @default.
• W4384282742 hasConcept C154945302 @default.
• W4384282742 hasConcept C165801399 @default.
• W4384282742 hasConcept C41008148 @default.
• W4384282742 hasConcept C66322947 @default.
• W4384282742 hasConcept C89600930 @default.
• W4384282742 hasConceptScore W4384282742C119599485 @default.
• W4384282742 hasConceptScore W4384282742C127413603 @default.
• W4384282742 hasConceptScore W4384282742C153180895 @default.
• W4384282742 hasConceptScore W4384282742C154945302 @default.
• W4384282742 hasConceptScore W4384282742C165801399 @default.
• W4384282742 hasConceptScore W4384282742C41008148 @default.
• W4384282742 hasConceptScore W4384282742C66322947 @default.
• W4384282742 hasConceptScore W4384282742C89600930 @default.
• W4384282742 hasFunder F4320319601 @default.
• W4384282742 hasFunder F4320321001 @default.
• W4384282742 hasFunder F4320321878 @default.
• W4384282742 hasFunder F4320335787 @default.
• W4384282742 hasIssue "8" @default.
• W4384282742 hasLocation W43842827421 @default.
• W4384282742 hasOpenAccess W4384282742 @default.
• W4384282742 hasPrimaryLocation W43842827421 @default.
• W4384282742 hasRelatedWork W2005437358 @default.
• W4384282742 hasRelatedWork W2033914206 @default.
• W4384282742 hasRelatedWork W2042327336 @default.
• W4384282742 hasRelatedWork W2046077695 @default.
• W4384282742 hasRelatedWork W2146076056 @default.
• W4384282742 hasRelatedWork W2163831990 @default.
• W4384282742 hasRelatedWork W2358941527 @default.
• W4384282742 hasRelatedWork W2378160586 @default.

• next