FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210686732> ?p ?o ?g. }

• W3210686732 abstract "Spectral graph convolutional networks (GCNs) are particular deep models which aim at extending neural networks to arbitrary irregular domains. The principle of these networks consists in projecting graph signals using the eigen-decomposition of their Laplacians, then achieving filtering in the spectral domain prior to back-project the resulting filtered signals onto the input graph domain. However, the success of these operations is highly dependent on the relevance of the used Laplacians which are mostly handcrafted and this makes GCNs clearly sub-optimal. In this paper, we introduce a novel spectral GCN that learns not only the usual convolutional parameters but also the Laplacian operators. The latter are designed end-to-end as a part of a recursive Chebyshev decomposition with the particularity of conveying both the differential and the non-differential properties of the learned representations – with increasing order and discrimination power – without overparametrizing the trained GCNs. Extensive experiments, conducted on the challenging task of skeleton-based action recognition, show the generalization ability and the outperformance of our proposed Laplacian design w.r.t. different baselines (built upon handcrafted and other learned Laplacians) as well as the related work." @default.
• W3210686732 created "2021-11-08" @default.
• W3210686732 creator A5029896607 @default.
• W3210686732 date "2021-10-01" @default.
• W3210686732 modified "2023-10-12" @default.
• W3210686732 title "Learning Laplacians in Chebyshev Graph Convolutional Networks" @default.
• W3210686732 cites W1501856433 @default.
• W3210686732 cites W1536680647 @default.
• W3210686732 cites W1601437336 @default.
• W3210686732 cites W1969117674 @default.
• W3210686732 cites W1972649231 @default.
• W3210686732 cites W1983592444 @default.
• W3210686732 cites W1993666393 @default.
• W3210686732 cites W2039182213 @default.
• W3210686732 cites W2048818249 @default.
• W3210686732 cites W2048821851 @default.
• W3210686732 cites W2049033299 @default.
• W3210686732 cites W2055588122 @default.
• W3210686732 cites W2058256495 @default.
• W3210686732 cites W2069797086 @default.
• W3210686732 cites W2085735683 @default.
• W3210686732 cites W2097308346 @default.
• W3210686732 cites W2101491865 @default.
• W3210686732 cites W2139906443 @default.
• W3210686732 cites W2162977472 @default.
• W3210686732 cites W2194775991 @default.
• W3210686732 cites W2230000137 @default.
• W3210686732 cites W2262590463 @default.
• W3210686732 cites W2342662179 @default.
• W3210686732 cites W2399164823 @default.
• W3210686732 cites W2443602434 @default.
• W3210686732 cites W2465488276 @default.
• W3210686732 cites W2510185399 @default.
• W3210686732 cites W2558460151 @default.
• W3210686732 cites W2563154851 @default.
• W3210686732 cites W2591766052 @default.
• W3210686732 cites W2603861860 @default.
• W3210686732 cites W2605973302 @default.
• W3210686732 cites W2610919036 @default.
• W3210686732 cites W2612707971 @default.
• W3210686732 cites W2778523960 @default.
• W3210686732 cites W2806008205 @default.
• W3210686732 cites W2905571172 @default.
• W3210686732 cites W2938493800 @default.
• W3210686732 cites W2940204692 @default.
• W3210686732 cites W2952200000 @default.
• W3210686732 cites W2962886701 @default.
• W3210686732 cites W2963076818 @default.
• W3210686732 cites W2963084622 @default.
• W3210686732 cites W2963369114 @default.
• W3210686732 cites W2963370140 @default.
• W3210686732 cites W2963382544 @default.
• W3210686732 cites W2964012239 @default.
• W3210686732 cites W2964171990 @default.
• W3210686732 cites W2966210862 @default.
• W3210686732 cites W3105136071 @default.
• W3210686732 cites W3109923889 @default.
• W3210686732 cites W3123784868 @default.
• W3210686732 cites W4230005465 @default.
• W3210686732 doi "https://doi.org/10.1109/iccvw54120.2021.00234" @default.
• W3210686732 hasPublicationYear "2021" @default.
• W3210686732 type Work @default.
• W3210686732 sameAs 3210686732 @default.
• W3210686732 citedByCount "5" @default.
• W3210686732 countsByYear W32106867322021 @default.
• W3210686732 countsByYear W32106867322022 @default.
• W3210686732 countsByYear W32106867322023 @default.
• W3210686732 crossrefType "proceedings-article" @default.
• W3210686732 hasAuthorship W3210686732A5029896607 @default.
• W3210686732 hasBestOaLocation W32106867322 @default.
• W3210686732 hasConcept C11413529 @default.
• W3210686732 hasConcept C115178988 @default.
• W3210686732 hasConcept C129785596 @default.
• W3210686732 hasConcept C132525143 @default.
• W3210686732 hasConcept C134306372 @default.
• W3210686732 hasConcept C153180895 @default.
• W3210686732 hasConcept C154945302 @default.
• W3210686732 hasConcept C165700671 @default.
• W3210686732 hasConcept C177148314 @default.
• W3210686732 hasConcept C203776342 @default.
• W3210686732 hasConcept C21424316 @default.
• W3210686732 hasConcept C22149727 @default.
• W3210686732 hasConcept C31972630 @default.
• W3210686732 hasConcept C33923547 @default.
• W3210686732 hasConcept C41008148 @default.
• W3210686732 hasConcept C74003402 @default.
• W3210686732 hasConcept C80444323 @default.
• W3210686732 hasConcept C81363708 @default.
• W3210686732 hasConceptScore W3210686732C11413529 @default.
• W3210686732 hasConceptScore W3210686732C115178988 @default.
• W3210686732 hasConceptScore W3210686732C129785596 @default.
• W3210686732 hasConceptScore W3210686732C132525143 @default.
• W3210686732 hasConceptScore W3210686732C134306372 @default.
• W3210686732 hasConceptScore W3210686732C153180895 @default.
• W3210686732 hasConceptScore W3210686732C154945302 @default.
• W3210686732 hasConceptScore W3210686732C165700671 @default.
• W3210686732 hasConceptScore W3210686732C177148314 @default.
• W3210686732 hasConceptScore W3210686732C203776342 @default.
• W3210686732 hasConceptScore W3210686732C21424316 @default.
• W3210686732 hasConceptScore W3210686732C22149727 @default.

• next