FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319661804> ?p ?o ?g. }

• W4319661804 endingPage "11842" @default.
• W4319661804 startingPage "11833" @default.
• W4319661804 abstract "In skeleton-based action recognition, treating skeleton data as pseudoimages using convolutional neural networks (CNNs) has proven to be effective. However, among existing CNN-based approaches, most focus on modeling information at the joint-level ignoring the size and direction information of the skeleton edges, which play an important role in action recognition, and these approaches may not be optimal. In addition, combining the directionality of human motion to portray action motion variation information is rarely considered in existing approaches, although it is more natural and reasonable for action sequence modeling. In this work, we propose a novel direction-guided two-stream convolutional neural network for skeleton-based action recognition. In the first stream, our model focuses on our defined edge-level information (including edge and edge_motion information) with directionality in the skeleton data to explore the spatiotemporal features of the action. In the second stream, since the motion is directional, we define different skeleton edge directions and extract different motion information (including translation and rotation information) in different directions to better exploit the motion features of the action. In addition, we propose a description of human motion inscribed by a combination of translation and rotation, and explore how they are integrated. We conducted extensive experiments on two challenging datasets, the NTU-RGB+D 60 and NTU-RGB+D 120 datasets, to verify the superiority of our proposed method over state-of-the-art methods. The experimental results demonstrate that the proposed direction-guided edge-level information and motion information complement each other for better action recognition." @default.
• W4319661804 created "2023-02-10" @default.
• W4319661804 creator A5022444559 @default.
• W4319661804 creator A5029337392 @default.
• W4319661804 creator A5029360035 @default.
• W4319661804 creator A5067301854 @default.
• W4319661804 date "2023-02-09" @default.
• W4319661804 modified "2023-09-23" @default.
• W4319661804 title "Direction-guided two-stream convolutional neural networks for skeleton-based action recognition" @default.
• W4319661804 cites W2415469094 @default.
• W4319661804 cites W2510185399 @default.
• W4319661804 cites W2554408731 @default.
• W4319661804 cites W2593146028 @default.
• W4319661804 cites W2603861860 @default.
• W4319661804 cites W2613570903 @default.
• W4319661804 cites W2793547936 @default.
• W4319661804 cites W2868755588 @default.
• W4319661804 cites W2923181798 @default.
• W4319661804 cites W2940457086 @default.
• W4319661804 cites W2944006115 @default.
• W4319661804 cites W2948246283 @default.
• W4319661804 cites W2963076818 @default.
• W4319661804 cites W2963369114 @default.
• W4319661804 cites W2964134613 @default.
• W4319661804 cites W2990541775 @default.
• W4319661804 cites W2991376513 @default.
• W4319661804 cites W3040842087 @default.
• W4319661804 cites W3080318329 @default.
• W4319661804 cites W3103858256 @default.
• W4319661804 cites W3106677303 @default.
• W4319661804 cites W3123784868 @default.
• W4319661804 cites W3130734881 @default.
• W4319661804 cites W3161491200 @default.
• W4319661804 cites W3172117784 @default.
• W4319661804 cites W3177913374 @default.
• W4319661804 cites W3216289472 @default.
• W4319661804 cites W4236008931 @default.
• W4319661804 cites W4240042586 @default.
• W4319661804 cites W4296438114 @default.
• W4319661804 doi "https://doi.org/10.1007/s00500-023-07862-1" @default.
• W4319661804 hasPublicationYear "2023" @default.
• W4319661804 type Work @default.
• W4319661804 citedByCount "0" @default.
• W4319661804 crossrefType "journal-article" @default.
• W4319661804 hasAuthorship W4319661804A5022444559 @default.
• W4319661804 hasAuthorship W4319661804A5029337392 @default.
• W4319661804 hasAuthorship W4319661804A5029360035 @default.
• W4319661804 hasAuthorship W4319661804A5067301854 @default.
• W4319661804 hasBestOaLocation W43196618042 @default.
• W4319661804 hasConcept C104114177 @default.
• W4319661804 hasConcept C104317684 @default.
• W4319661804 hasConcept C105580179 @default.
• W4319661804 hasConcept C149364088 @default.
• W4319661804 hasConcept C153180895 @default.
• W4319661804 hasConcept C154945302 @default.
• W4319661804 hasConcept C162307627 @default.
• W4319661804 hasConcept C185592680 @default.
• W4319661804 hasConcept C18969341 @default.
• W4319661804 hasConcept C199360897 @default.
• W4319661804 hasConcept C2777846634 @default.
• W4319661804 hasConcept C31972630 @default.
• W4319661804 hasConcept C41008148 @default.
• W4319661804 hasConcept C55493867 @default.
• W4319661804 hasConcept C74050887 @default.
• W4319661804 hasConcept C81363708 @default.
• W4319661804 hasConcept C82990744 @default.
• W4319661804 hasConceptScore W4319661804C104114177 @default.
• W4319661804 hasConceptScore W4319661804C104317684 @default.
• W4319661804 hasConceptScore W4319661804C105580179 @default.
• W4319661804 hasConceptScore W4319661804C149364088 @default.
• W4319661804 hasConceptScore W4319661804C153180895 @default.
• W4319661804 hasConceptScore W4319661804C154945302 @default.
• W4319661804 hasConceptScore W4319661804C162307627 @default.
• W4319661804 hasConceptScore W4319661804C185592680 @default.
• W4319661804 hasConceptScore W4319661804C18969341 @default.
• W4319661804 hasConceptScore W4319661804C199360897 @default.
• W4319661804 hasConceptScore W4319661804C2777846634 @default.
• W4319661804 hasConceptScore W4319661804C31972630 @default.
• W4319661804 hasConceptScore W4319661804C41008148 @default.
• W4319661804 hasConceptScore W4319661804C55493867 @default.
• W4319661804 hasConceptScore W4319661804C74050887 @default.
• W4319661804 hasConceptScore W4319661804C81363708 @default.
• W4319661804 hasConceptScore W4319661804C82990744 @default.
• W4319661804 hasIssue "16" @default.
• W4319661804 hasLocation W43196618041 @default.
• W4319661804 hasLocation W43196618042 @default.
• W4319661804 hasOpenAccess W4319661804 @default.
• W4319661804 hasPrimaryLocation W43196618041 @default.
• W4319661804 hasRelatedWork W2119189625 @default.
• W4319661804 hasRelatedWork W2144724818 @default.
• W4319661804 hasRelatedWork W2360758025 @default.
• W4319661804 hasRelatedWork W2401401198 @default.
• W4319661804 hasRelatedWork W2412051338 @default.
• W4319661804 hasRelatedWork W2806706403 @default.
• W4319661804 hasRelatedWork W2940661641 @default.
• W4319661804 hasRelatedWork W2989915422 @default.
• W4319661804 hasRelatedWork W3131297908 @default.
• W4319661804 hasRelatedWork W3135923011 @default.

• next