Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308238196> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4308238196 abstract "Spatial-temporal graph convolutional networks (ST-GCNs) have been successfully applied for dynamic graphs representation learning, such as modeling skeleton-based human actions. However, ST-GCNs embed these non-Euclidean graph structures into Euclidean space, which is not the natural space to represent such structures as embedding them in this space incurs a large distortion. In this work, we make use of hyperbolic non-Euclidean geometry and construct compact ST-GCNs in the hyperbolic space. It can be shown that hyperbolic ST-GCNs (HST-GCNs) outperform the corresponding Euclidean counterparts. Additionally, these compact hyperbolic models can be used to increase the performance of large complex Euclidean models. Moreover, we show that the same or even better performance of large Euclidean models can be achieved by fusing the scores of smaller Euclidean models and a compact hyperbolic model. This in turn leads to reducing the total number of model parameters and hence model size. To validate the performance of these hyperbolic networks, we conducted extensive experiments on NTU RGB+D, NTU RGB+D 120 and Kinectics-Skeleton datasets for human action recognition." @default.
- W4308238196 created "2022-11-09" @default.
- W4308238196 creator A5015798963 @default.
- W4308238196 creator A5019479187 @default.
- W4308238196 creator A5082301986 @default.
- W4308238196 date "2022-10-16" @default.
- W4308238196 modified "2023-09-30" @default.
- W4308238196 title "Hyperbolic Spatial Temporal Graph Convolutional Networks" @default.
- W4308238196 cites W2048821851 @default.
- W4308238196 cites W2603861860 @default.
- W4308238196 cites W2613570903 @default.
- W4308238196 cites W2940457086 @default.
- W4308238196 cites W2948058585 @default.
- W4308238196 cites W2963076818 @default.
- W4308238196 cites W2963465695 @default.
- W4308238196 cites W2964134613 @default.
- W4308238196 cites W2996835428 @default.
- W4308238196 cites W2997769980 @default.
- W4308238196 cites W3035050855 @default.
- W4308238196 cites W3035225512 @default.
- W4308238196 cites W3092654784 @default.
- W4308238196 cites W3093411241 @default.
- W4308238196 cites W3099014939 @default.
- W4308238196 cites W3108496296 @default.
- W4308238196 cites W4235484205 @default.
- W4308238196 doi "https://doi.org/10.1109/icip46576.2022.9897522" @default.
- W4308238196 hasPublicationYear "2022" @default.
- W4308238196 type Work @default.
- W4308238196 citedByCount "2" @default.
- W4308238196 countsByYear W43082381962022 @default.
- W4308238196 countsByYear W43082381962023 @default.
- W4308238196 crossrefType "proceedings-article" @default.
- W4308238196 hasAuthorship W4308238196A5015798963 @default.
- W4308238196 hasAuthorship W4308238196A5019479187 @default.
- W4308238196 hasAuthorship W4308238196A5082301986 @default.
- W4308238196 hasBestOaLocation W43082381962 @default.
- W4308238196 hasConcept C11413529 @default.
- W4308238196 hasConcept C114614502 @default.
- W4308238196 hasConcept C120174047 @default.
- W4308238196 hasConcept C129782007 @default.
- W4308238196 hasConcept C132525143 @default.
- W4308238196 hasConcept C153180895 @default.
- W4308238196 hasConcept C154945302 @default.
- W4308238196 hasConcept C171558263 @default.
- W4308238196 hasConcept C186450821 @default.
- W4308238196 hasConcept C202444582 @default.
- W4308238196 hasConcept C2524010 @default.
- W4308238196 hasConcept C33923547 @default.
- W4308238196 hasConcept C41008148 @default.
- W4308238196 hasConcept C41608201 @default.
- W4308238196 hasConcept C80444323 @default.
- W4308238196 hasConcept C81363708 @default.
- W4308238196 hasConcept C82990744 @default.
- W4308238196 hasConcept C83677898 @default.
- W4308238196 hasConceptScore W4308238196C11413529 @default.
- W4308238196 hasConceptScore W4308238196C114614502 @default.
- W4308238196 hasConceptScore W4308238196C120174047 @default.
- W4308238196 hasConceptScore W4308238196C129782007 @default.
- W4308238196 hasConceptScore W4308238196C132525143 @default.
- W4308238196 hasConceptScore W4308238196C153180895 @default.
- W4308238196 hasConceptScore W4308238196C154945302 @default.
- W4308238196 hasConceptScore W4308238196C171558263 @default.
- W4308238196 hasConceptScore W4308238196C186450821 @default.
- W4308238196 hasConceptScore W4308238196C202444582 @default.
- W4308238196 hasConceptScore W4308238196C2524010 @default.
- W4308238196 hasConceptScore W4308238196C33923547 @default.
- W4308238196 hasConceptScore W4308238196C41008148 @default.
- W4308238196 hasConceptScore W4308238196C41608201 @default.
- W4308238196 hasConceptScore W4308238196C80444323 @default.
- W4308238196 hasConceptScore W4308238196C81363708 @default.
- W4308238196 hasConceptScore W4308238196C82990744 @default.
- W4308238196 hasConceptScore W4308238196C83677898 @default.
- W4308238196 hasLocation W43082381961 @default.
- W4308238196 hasLocation W43082381962 @default.
- W4308238196 hasOpenAccess W4308238196 @default.
- W4308238196 hasPrimaryLocation W43082381961 @default.
- W4308238196 hasRelatedWork W1638832135 @default.
- W4308238196 hasRelatedWork W2053578961 @default.
- W4308238196 hasRelatedWork W2105228010 @default.
- W4308238196 hasRelatedWork W2592898389 @default.
- W4308238196 hasRelatedWork W2749646986 @default.
- W4308238196 hasRelatedWork W2947897749 @default.
- W4308238196 hasRelatedWork W4229699757 @default.
- W4308238196 hasRelatedWork W4281992692 @default.
- W4308238196 hasRelatedWork W4296950832 @default.
- W4308238196 hasRelatedWork W65248374 @default.
- W4308238196 isParatext "false" @default.
- W4308238196 isRetracted "false" @default.
- W4308238196 workType "article" @default.