Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387492890> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4387492890 endingPage "126915" @default.
- W4387492890 startingPage "126915" @default.
- W4387492890 abstract "Graph convolutional networks (GCN) have become the mainstream in skeleton-based action recognition. For further performance improvement, existing methods propose to utilize self-attention to model long-range features of joints. However, these methods cannot balance accuracy with computational efficiency. In this paper, we propose the Switching Partition Strategy (SPAR) Network that uses the self-attention mechanism for the simultaneous and efficient extraction of spatial–temporal long-range information from the skeleton. We design two partition strategies that reduce the computational cost and improve the efficiency of the computation of self-attention. Extensive experiments are conducted on two large-scale datasets, i.e. NTU RGB+D 60 and NTU RGB+D 120, to evaluate the performance of the proposed SPAR network. The results demonstrate that our method outperforms the state-of-the-art on accuracy as well as computational cost." @default.
- W4387492890 created "2023-10-11" @default.
- W4387492890 creator A5036654398 @default.
- W4387492890 creator A5037529768 @default.
- W4387492890 creator A5048965499 @default.
- W4387492890 creator A5067207088 @default.
- W4387492890 date "2023-10-01" @default.
- W4387492890 modified "2023-10-12" @default.
- W4387492890 title "SPAR: An efficient self-attention network using Switching Partition Strategy for skeleton-based action recognition" @default.
- W4387492890 cites W2064675550 @default.
- W4387492890 cites W2096214539 @default.
- W4387492890 cites W2342776425 @default.
- W4387492890 cites W2470673105 @default.
- W4387492890 cites W2606294640 @default.
- W4387492890 cites W2736334449 @default.
- W4387492890 cites W2737725206 @default.
- W4387492890 cites W2782776028 @default.
- W4387492890 cites W2940457086 @default.
- W4387492890 cites W2944006115 @default.
- W4387492890 cites W2948058585 @default.
- W4387492890 cites W2950568498 @default.
- W4387492890 cites W2962722475 @default.
- W4387492890 cites W2963076818 @default.
- W4387492890 cites W2963091558 @default.
- W4387492890 cites W2963465695 @default.
- W4387492890 cites W2963954913 @default.
- W4387492890 cites W2964134613 @default.
- W4387492890 cites W3009946848 @default.
- W4387492890 cites W3035050855 @default.
- W4387492890 cites W3035225512 @default.
- W4387492890 cites W3092336341 @default.
- W4387492890 cites W3138516171 @default.
- W4387492890 cites W3174836262 @default.
- W4387492890 cites W4200301490 @default.
- W4387492890 doi "https://doi.org/10.1016/j.neucom.2023.126915" @default.
- W4387492890 hasPublicationYear "2023" @default.
- W4387492890 type Work @default.
- W4387492890 citedByCount "0" @default.
- W4387492890 crossrefType "journal-article" @default.
- W4387492890 hasAuthorship W4387492890A5036654398 @default.
- W4387492890 hasAuthorship W4387492890A5037529768 @default.
- W4387492890 hasAuthorship W4387492890A5048965499 @default.
- W4387492890 hasAuthorship W4387492890A5067207088 @default.
- W4387492890 hasConcept C11413529 @default.
- W4387492890 hasConcept C114614502 @default.
- W4387492890 hasConcept C119857082 @default.
- W4387492890 hasConcept C127413603 @default.
- W4387492890 hasConcept C132525143 @default.
- W4387492890 hasConcept C153180895 @default.
- W4387492890 hasConcept C154945302 @default.
- W4387492890 hasConcept C2776698545 @default.
- W4387492890 hasConcept C33923547 @default.
- W4387492890 hasConcept C41008148 @default.
- W4387492890 hasConcept C42812 @default.
- W4387492890 hasConcept C45374587 @default.
- W4387492890 hasConcept C66938386 @default.
- W4387492890 hasConcept C80444323 @default.
- W4387492890 hasConcept C82990744 @default.
- W4387492890 hasConceptScore W4387492890C11413529 @default.
- W4387492890 hasConceptScore W4387492890C114614502 @default.
- W4387492890 hasConceptScore W4387492890C119857082 @default.
- W4387492890 hasConceptScore W4387492890C127413603 @default.
- W4387492890 hasConceptScore W4387492890C132525143 @default.
- W4387492890 hasConceptScore W4387492890C153180895 @default.
- W4387492890 hasConceptScore W4387492890C154945302 @default.
- W4387492890 hasConceptScore W4387492890C2776698545 @default.
- W4387492890 hasConceptScore W4387492890C33923547 @default.
- W4387492890 hasConceptScore W4387492890C41008148 @default.
- W4387492890 hasConceptScore W4387492890C42812 @default.
- W4387492890 hasConceptScore W4387492890C45374587 @default.
- W4387492890 hasConceptScore W4387492890C66938386 @default.
- W4387492890 hasConceptScore W4387492890C80444323 @default.
- W4387492890 hasConceptScore W4387492890C82990744 @default.
- W4387492890 hasLocation W43874928901 @default.
- W4387492890 hasOpenAccess W4387492890 @default.
- W4387492890 hasPrimaryLocation W43874928901 @default.
- W4387492890 hasRelatedWork W2016723836 @default.
- W4387492890 hasRelatedWork W2031289439 @default.
- W4387492890 hasRelatedWork W2074687562 @default.
- W4387492890 hasRelatedWork W2090859341 @default.
- W4387492890 hasRelatedWork W2292511027 @default.
- W4387492890 hasRelatedWork W2356200252 @default.
- W4387492890 hasRelatedWork W2366018118 @default.
- W4387492890 hasRelatedWork W2370682031 @default.
- W4387492890 hasRelatedWork W2407361169 @default.
- W4387492890 hasRelatedWork W4229364042 @default.
- W4387492890 isParatext "false" @default.
- W4387492890 isRetracted "false" @default.
- W4387492890 workType "article" @default.