Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129873480> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3129873480 abstract "Learning graph convolutional networks (GCNs) is an emerging field which aims at generalizing deep learning to arbitrary non-regular domains. Most of the existing GCNs follow a neighborhood aggregation scheme, where the representation of a node is recursively obtained by aggregating its neighboring node representations using averaging or sorting operations. However, these operations are either ill-posed or weak to be discriminant or increase the number of training parameters and thereby the computational complexity and the risk of overfitting. In this paper, we introduce a novel GCN framework that achieves spatial graph convolution in a reproducing kernel Hilbert space. The latter makes it possible to design, via implicit kernel representations, convolutional graph filters in a high dimensional and more discriminating space without increasing the number of training parameters. The particularity of our GCN model also resides in its ability to achieve convolutions without explicitly realigning nodes in the receptive fields of the learned graph filters with those of the input graphs, thereby making convolutions permutation agnostic and well defined. Experiments conducted on the challenging task of skeleton-based action recognition show the superiority of the proposed method against different baselines as well as the related work." @default.
- W3129873480 created "2021-03-01" @default.
- W3129873480 creator A5029896607 @default.
- W3129873480 date "2021-01-10" @default.
- W3129873480 modified "2023-09-30" @default.
- W3129873480 title "Kernel-based Graph Convolutional Networks" @default.
- W3129873480 cites W1501856433 @default.
- W3129873480 cites W1510073064 @default.
- W3129873480 cites W1601437336 @default.
- W3129873480 cites W1969117674 @default.
- W3129873480 cites W2002355073 @default.
- W3129873480 cites W2039182213 @default.
- W3129873480 cites W2067022618 @default.
- W3129873480 cites W2069797086 @default.
- W3129873480 cites W2109235804 @default.
- W3129873480 cites W2132285904 @default.
- W3129873480 cites W2139906443 @default.
- W3129873480 cites W2149298154 @default.
- W3129873480 cites W2230000137 @default.
- W3129873480 cites W2399164823 @default.
- W3129873480 cites W2558460151 @default.
- W3129873480 cites W2591766052 @default.
- W3129873480 cites W2603861860 @default.
- W3129873480 cites W2940204692 @default.
- W3129873480 cites W3105136071 @default.
- W3129873480 cites W3123784868 @default.
- W3129873480 doi "https://doi.org/10.1109/icpr48806.2021.9412311" @default.
- W3129873480 hasPublicationYear "2021" @default.
- W3129873480 type Work @default.
- W3129873480 sameAs 3129873480 @default.
- W3129873480 citedByCount "4" @default.
- W3129873480 countsByYear W31298734802021 @default.
- W3129873480 countsByYear W31298734802022 @default.
- W3129873480 countsByYear W31298734802023 @default.
- W3129873480 crossrefType "proceedings-article" @default.
- W3129873480 hasAuthorship W3129873480A5029896607 @default.
- W3129873480 hasBestOaLocation W31298734802 @default.
- W3129873480 hasConcept C11413529 @default.
- W3129873480 hasConcept C118615104 @default.
- W3129873480 hasConcept C132525143 @default.
- W3129873480 hasConcept C153180895 @default.
- W3129873480 hasConcept C154945302 @default.
- W3129873480 hasConcept C22019652 @default.
- W3129873480 hasConcept C33923547 @default.
- W3129873480 hasConcept C41008148 @default.
- W3129873480 hasConcept C50644808 @default.
- W3129873480 hasConcept C74193536 @default.
- W3129873480 hasConcept C80444323 @default.
- W3129873480 hasConcept C81363708 @default.
- W3129873480 hasConceptScore W3129873480C11413529 @default.
- W3129873480 hasConceptScore W3129873480C118615104 @default.
- W3129873480 hasConceptScore W3129873480C132525143 @default.
- W3129873480 hasConceptScore W3129873480C153180895 @default.
- W3129873480 hasConceptScore W3129873480C154945302 @default.
- W3129873480 hasConceptScore W3129873480C22019652 @default.
- W3129873480 hasConceptScore W3129873480C33923547 @default.
- W3129873480 hasConceptScore W3129873480C41008148 @default.
- W3129873480 hasConceptScore W3129873480C50644808 @default.
- W3129873480 hasConceptScore W3129873480C74193536 @default.
- W3129873480 hasConceptScore W3129873480C80444323 @default.
- W3129873480 hasConceptScore W3129873480C81363708 @default.
- W3129873480 hasLocation W31298734801 @default.
- W3129873480 hasLocation W31298734802 @default.
- W3129873480 hasLocation W31298734803 @default.
- W3129873480 hasLocation W31298734804 @default.
- W3129873480 hasLocation W31298734805 @default.
- W3129873480 hasOpenAccess W3129873480 @default.
- W3129873480 hasPrimaryLocation W31298734801 @default.
- W3129873480 hasRelatedWork W3012393889 @default.
- W3129873480 hasRelatedWork W3081496756 @default.
- W3129873480 hasRelatedWork W3093612317 @default.
- W3129873480 hasRelatedWork W3127819136 @default.
- W3129873480 hasRelatedWork W3159557112 @default.
- W3129873480 hasRelatedWork W4210691109 @default.
- W3129873480 hasRelatedWork W4220996320 @default.
- W3129873480 hasRelatedWork W4309224979 @default.
- W3129873480 hasRelatedWork W4313289428 @default.
- W3129873480 hasRelatedWork W785854688 @default.
- W3129873480 isParatext "false" @default.
- W3129873480 isRetracted "false" @default.
- W3129873480 magId "3129873480" @default.
- W3129873480 workType "article" @default.