Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366999738> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4366999738 abstract "Skeleton-based action recognition has achieved remarkable results in human action recognition with the development of graph convolutional networks (GCNs). However, the recent works tend to construct complex learning mechanisms with redundant training and exist a bottleneck for long time-series. To solve these problems, we propose the Temporal-Spatio Graph ConvNeXt (TSGCNeXt) to explore efficient learning mechanism of long temporal skeleton sequences. Firstly, a new graph learning mechanism with simple structure, Dynamic-Static Separate Multi-graph Convolution (DS-SMG) is proposed to aggregate features of multiple independent topological graphs and avoid the node information being ignored during dynamic convolution. Next, we construct a graph convolution training acceleration mechanism to optimize the back-propagation computing of dynamic graph learning with 55.08% speed-up. Finally, the TSGCNeXt restructure the overall structure of GCN with three Spatio-temporal learning modules,efficiently modeling long temporal features. In comparison with existing previous methods on large-scale datasets NTU RGB+D 60 and 120, TSGCNeXt outperforms on single-stream networks. In addition, with the ema model introduced into the multi-stream fusion, TSGCNeXt achieves SOTA levels. On the cross-subject and cross-set of the NTU 120, accuracies reach 90.22% and 91.74%." @default.
- W4366999738 created "2023-04-27" @default.
- W4366999738 creator A5007362694 @default.
- W4366999738 creator A5022252196 @default.
- W4366999738 creator A5037547431 @default.
- W4366999738 creator A5043155449 @default.
- W4366999738 creator A5061488698 @default.
- W4366999738 creator A5061906681 @default.
- W4366999738 date "2023-04-23" @default.
- W4366999738 modified "2023-10-16" @default.
- W4366999738 title "TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential" @default.
- W4366999738 doi "https://doi.org/10.48550/arxiv.2304.11631" @default.
- W4366999738 hasPublicationYear "2023" @default.
- W4366999738 type Work @default.
- W4366999738 citedByCount "0" @default.
- W4366999738 crossrefType "posted-content" @default.
- W4366999738 hasAuthorship W4366999738A5007362694 @default.
- W4366999738 hasAuthorship W4366999738A5022252196 @default.
- W4366999738 hasAuthorship W4366999738A5037547431 @default.
- W4366999738 hasAuthorship W4366999738A5043155449 @default.
- W4366999738 hasAuthorship W4366999738A5061488698 @default.
- W4366999738 hasAuthorship W4366999738A5061906681 @default.
- W4366999738 hasBestOaLocation W43669997381 @default.
- W4366999738 hasConcept C11413529 @default.
- W4366999738 hasConcept C119857082 @default.
- W4366999738 hasConcept C132525143 @default.
- W4366999738 hasConcept C149635348 @default.
- W4366999738 hasConcept C153180895 @default.
- W4366999738 hasConcept C154945302 @default.
- W4366999738 hasConcept C2777212361 @default.
- W4366999738 hasConcept C2780513914 @default.
- W4366999738 hasConcept C2987834672 @default.
- W4366999738 hasConcept C41008148 @default.
- W4366999738 hasConcept C45347329 @default.
- W4366999738 hasConcept C50644808 @default.
- W4366999738 hasConcept C80444323 @default.
- W4366999738 hasConceptScore W4366999738C11413529 @default.
- W4366999738 hasConceptScore W4366999738C119857082 @default.
- W4366999738 hasConceptScore W4366999738C132525143 @default.
- W4366999738 hasConceptScore W4366999738C149635348 @default.
- W4366999738 hasConceptScore W4366999738C153180895 @default.
- W4366999738 hasConceptScore W4366999738C154945302 @default.
- W4366999738 hasConceptScore W4366999738C2777212361 @default.
- W4366999738 hasConceptScore W4366999738C2780513914 @default.
- W4366999738 hasConceptScore W4366999738C2987834672 @default.
- W4366999738 hasConceptScore W4366999738C41008148 @default.
- W4366999738 hasConceptScore W4366999738C45347329 @default.
- W4366999738 hasConceptScore W4366999738C50644808 @default.
- W4366999738 hasConceptScore W4366999738C80444323 @default.
- W4366999738 hasLocation W43669997381 @default.
- W4366999738 hasOpenAccess W4366999738 @default.
- W4366999738 hasPrimaryLocation W43669997381 @default.
- W4366999738 hasRelatedWork W1728708896 @default.
- W4366999738 hasRelatedWork W2726222394 @default.
- W4366999738 hasRelatedWork W2752217129 @default.
- W4366999738 hasRelatedWork W2941155331 @default.
- W4366999738 hasRelatedWork W3106494386 @default.
- W4366999738 hasRelatedWork W4200171239 @default.
- W4366999738 hasRelatedWork W4280619012 @default.
- W4366999738 hasRelatedWork W4293731510 @default.
- W4366999738 hasRelatedWork W4312501200 @default.
- W4366999738 hasRelatedWork W4315588138 @default.
- W4366999738 isParatext "false" @default.
- W4366999738 isRetracted "false" @default.
- W4366999738 workType "article" @default.