Matches in SemOpenAlex for { <https://semopenalex.org/work/W3193648372> ?p ?o ?g. }
- W3193648372 abstract "Graph convolutional networks (GCNs) aim at extending deep learning to arbitrary irregular domains, namely graphs. Their success is highly dependent on how the topology of input graphs is defined and most of the existing GCN architectures rely on predefined or handcrafted graph structures. In this paper, we introduce a novel method that learns the topology (or connectivity) of input graphs as a part of GCN design. The main contribution of our method resides in building an orthogonal connectivity basis that optimally aggregates nodes, through their neighborhood, prior to achieve convolution. Our method also considers a stochasticity criterion which acts as a regularizer that makes the learned basis and the underlying GCNs lightweight while still being highly effective. Experiments conducted on the challenging task of skeleton-based hand-gesture recognition show the high effectiveness of the learned GCNs w.r.t. the related work." @default.
- W3193648372 created "2021-08-30" @default.
- W3193648372 creator A5029896607 @default.
- W3193648372 date "2021-09-19" @default.
- W3193648372 modified "2023-10-15" @default.
- W3193648372 title "Lightweight Connectivity In Graph Convolutional Networks For Skeleton-Based Recognition" @default.
- W3193648372 cites W1601437336 @default.
- W3193648372 cites W1983592444 @default.
- W3193648372 cites W1992208818 @default.
- W3193648372 cites W2039182213 @default.
- W3193648372 cites W2048821851 @default.
- W3193648372 cites W2049033299 @default.
- W3193648372 cites W2085735683 @default.
- W3193648372 cites W2097117768 @default.
- W3193648372 cites W2194775991 @default.
- W3193648372 cites W2342662179 @default.
- W3193648372 cites W2395459784 @default.
- W3193648372 cites W2443602434 @default.
- W3193648372 cites W2465488276 @default.
- W3193648372 cites W2517500902 @default.
- W3193648372 cites W2551687757 @default.
- W3193648372 cites W2587063199 @default.
- W3193648372 cites W2605973302 @default.
- W3193648372 cites W2769171608 @default.
- W3193648372 cites W2806008205 @default.
- W3193648372 cites W2903909270 @default.
- W3193648372 cites W2919115771 @default.
- W3193648372 cites W2938493800 @default.
- W3193648372 cites W2963150697 @default.
- W3193648372 cites W2963369114 @default.
- W3193648372 cites W2963370140 @default.
- W3193648372 cites W2963382544 @default.
- W3193648372 cites W2963446712 @default.
- W3193648372 cites W2964012239 @default.
- W3193648372 cites W2964171990 @default.
- W3193648372 cites W4230005465 @default.
- W3193648372 doi "https://doi.org/10.1109/icip42928.2021.9506774" @default.
- W3193648372 hasPublicationYear "2021" @default.
- W3193648372 type Work @default.
- W3193648372 sameAs 3193648372 @default.
- W3193648372 citedByCount "2" @default.
- W3193648372 countsByYear W31936483722022 @default.
- W3193648372 countsByYear W31936483722023 @default.
- W3193648372 crossrefType "proceedings-article" @default.
- W3193648372 hasAuthorship W3193648372A5029896607 @default.
- W3193648372 hasBestOaLocation W31936483722 @default.
- W3193648372 hasConcept C108583219 @default.
- W3193648372 hasConcept C114614502 @default.
- W3193648372 hasConcept C12426560 @default.
- W3193648372 hasConcept C132525143 @default.
- W3193648372 hasConcept C153180895 @default.
- W3193648372 hasConcept C154945302 @default.
- W3193648372 hasConcept C157406716 @default.
- W3193648372 hasConcept C162324750 @default.
- W3193648372 hasConcept C184720557 @default.
- W3193648372 hasConcept C187736073 @default.
- W3193648372 hasConcept C18969341 @default.
- W3193648372 hasConcept C199360897 @default.
- W3193648372 hasConcept C203776342 @default.
- W3193648372 hasConcept C22149727 @default.
- W3193648372 hasConcept C2524010 @default.
- W3193648372 hasConcept C2780451532 @default.
- W3193648372 hasConcept C33923547 @default.
- W3193648372 hasConcept C41008148 @default.
- W3193648372 hasConcept C45347329 @default.
- W3193648372 hasConcept C50644808 @default.
- W3193648372 hasConcept C80444323 @default.
- W3193648372 hasConceptScore W3193648372C108583219 @default.
- W3193648372 hasConceptScore W3193648372C114614502 @default.
- W3193648372 hasConceptScore W3193648372C12426560 @default.
- W3193648372 hasConceptScore W3193648372C132525143 @default.
- W3193648372 hasConceptScore W3193648372C153180895 @default.
- W3193648372 hasConceptScore W3193648372C154945302 @default.
- W3193648372 hasConceptScore W3193648372C157406716 @default.
- W3193648372 hasConceptScore W3193648372C162324750 @default.
- W3193648372 hasConceptScore W3193648372C184720557 @default.
- W3193648372 hasConceptScore W3193648372C187736073 @default.
- W3193648372 hasConceptScore W3193648372C18969341 @default.
- W3193648372 hasConceptScore W3193648372C199360897 @default.
- W3193648372 hasConceptScore W3193648372C203776342 @default.
- W3193648372 hasConceptScore W3193648372C22149727 @default.
- W3193648372 hasConceptScore W3193648372C2524010 @default.
- W3193648372 hasConceptScore W3193648372C2780451532 @default.
- W3193648372 hasConceptScore W3193648372C33923547 @default.
- W3193648372 hasConceptScore W3193648372C41008148 @default.
- W3193648372 hasConceptScore W3193648372C45347329 @default.
- W3193648372 hasConceptScore W3193648372C50644808 @default.
- W3193648372 hasConceptScore W3193648372C80444323 @default.
- W3193648372 hasLocation W31936483721 @default.
- W3193648372 hasLocation W31936483722 @default.
- W3193648372 hasLocation W31936483723 @default.
- W3193648372 hasLocation W31936483724 @default.
- W3193648372 hasLocation W31936483725 @default.
- W3193648372 hasOpenAccess W3193648372 @default.
- W3193648372 hasPrimaryLocation W31936483721 @default.
- W3193648372 hasRelatedWork W2078609410 @default.
- W3193648372 hasRelatedWork W2105938841 @default.
- W3193648372 hasRelatedWork W2334655667 @default.
- W3193648372 hasRelatedWork W2464530384 @default.
- W3193648372 hasRelatedWork W2611989081 @default.