FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3106677303> ?p ?o ?g. }

• W3106677303 endingPage "300" @default.
• W3106677303 startingPage "288" @default.
• W3106677303 abstract "Skeleton based human action recognition has attracted more and more attentions recently thanks to the accessibility of depth sensors and the development of pose estimation techniques. Conventional approaches such as convolutional neural networks usually model skeletons with grid-shaped representations, which cannot explicitly explore the dependency between two correlated joints. In this paper, we treat the skeleton as a single graph with joints as nodes and bones as edges. Based on the skeleton graph, the improved graph convolutional network called adaptive multi-view graph convolutional networks(AMV-GCNs) is proposed to deal with skeleton based action recognition. We firstly construct a novel skeleton graph and two kinds of graph nodes are defined to model the spatial configuration and temporal dynamics respectively. Then the generated graphs along with feature vectors on graph nodes are fed into AMV-GCNs. In AMV-GCNs, an adaptive view transformation module is designed to reduce the impact of view diversity. Proposed module can automatically determine suitable viewpoints and transform skeletons to new representations under those viewpoints for better recognition. Further, we employ multiple GCNs based streams to utilize and learn action information from different viewpoints. Finally, the classification scores from multiple streams are fused to provide the recognition result. Extensive experimental evaluations on four challenging datasets, NTU RGB+D 60, NTU RGB+D 120, Northwestern-UCLA and UTD-MHAD, demonstrate the superiority of our proposed network." @default.
• W3106677303 created "2020-12-07" @default.
• W3106677303 creator A5000124250 @default.
• W3106677303 creator A5052785922 @default.
• W3106677303 creator A5086770271 @default.
• W3106677303 date "2021-07-01" @default.
• W3106677303 modified "2023-10-14" @default.
• W3106677303 title "Adaptive multi-view graph convolutional networks for skeleton-based action recognition" @default.
• W3106677303 cites W2054041160 @default.
• W3106677303 cites W2060280062 @default.
• W3106677303 cites W2086693793 @default.
• W3106677303 cites W2104696249 @default.
• W3106677303 cites W2145546283 @default.
• W3106677303 cites W2235034809 @default.
• W3106677303 cites W2295474072 @default.
• W3106677303 cites W2409643086 @default.
• W3106677303 cites W2554408731 @default.
• W3106677303 cites W2563154851 @default.
• W3106677303 cites W2565070966 @default.
• W3106677303 cites W2593146028 @default.
• W3106677303 cites W2716916105 @default.
• W3106677303 cites W2745797847 @default.
• W3106677303 cites W2787262181 @default.
• W3106677303 cites W2793547936 @default.
• W3106677303 cites W2797382244 @default.
• W3106677303 cites W2799211965 @default.
• W3106677303 cites W2799409595 @default.
• W3106677303 cites W2884286326 @default.
• W3106677303 cites W2899936784 @default.
• W3106677303 cites W2905706796 @default.
• W3106677303 cites W2914177721 @default.
• W3106677303 cites W2923181798 @default.
• W3106677303 cites W2943173229 @default.
• W3106677303 cites W2944006115 @default.
• W3106677303 cites W2963282966 @default.
• W3106677303 cites W2963369114 @default.
• W3106677303 cites W2964134613 @default.
• W3106677303 cites W2965909452 @default.
• W3106677303 cites W3034999503 @default.
• W3106677303 cites W3099014939 @default.
• W3106677303 cites W3103858256 @default.
• W3106677303 cites W3123784868 @default.
• W3106677303 doi "https://doi.org/10.1016/j.neucom.2020.03.126" @default.
• W3106677303 hasPublicationYear "2021" @default.
• W3106677303 type Work @default.
• W3106677303 sameAs 3106677303 @default.
• W3106677303 citedByCount "22" @default.
• W3106677303 countsByYear W31066773032020 @default.
• W3106677303 countsByYear W31066773032021 @default.
• W3106677303 countsByYear W31066773032022 @default.
• W3106677303 countsByYear W31066773032023 @default.
• W3106677303 crossrefType "journal-article" @default.
• W3106677303 hasAuthorship W3106677303A5000124250 @default.
• W3106677303 hasAuthorship W3106677303A5052785922 @default.
• W3106677303 hasAuthorship W3106677303A5086770271 @default.
• W3106677303 hasConcept C132525143 @default.
• W3106677303 hasConcept C142362112 @default.
• W3106677303 hasConcept C153180895 @default.
• W3106677303 hasConcept C153349607 @default.
• W3106677303 hasConcept C154945302 @default.
• W3106677303 hasConcept C18969341 @default.
• W3106677303 hasConcept C199360897 @default.
• W3106677303 hasConcept C2776035091 @default.
• W3106677303 hasConcept C2777212361 @default.
• W3106677303 hasConcept C2987834672 @default.
• W3106677303 hasConcept C41008148 @default.
• W3106677303 hasConcept C80444323 @default.
• W3106677303 hasConcept C81363708 @default.
• W3106677303 hasConcept C82990744 @default.
• W3106677303 hasConceptScore W3106677303C132525143 @default.
• W3106677303 hasConceptScore W3106677303C142362112 @default.
• W3106677303 hasConceptScore W3106677303C153180895 @default.
• W3106677303 hasConceptScore W3106677303C153349607 @default.
• W3106677303 hasConceptScore W3106677303C154945302 @default.
• W3106677303 hasConceptScore W3106677303C18969341 @default.
• W3106677303 hasConceptScore W3106677303C199360897 @default.
• W3106677303 hasConceptScore W3106677303C2776035091 @default.
• W3106677303 hasConceptScore W3106677303C2777212361 @default.
• W3106677303 hasConceptScore W3106677303C2987834672 @default.
• W3106677303 hasConceptScore W3106677303C41008148 @default.
• W3106677303 hasConceptScore W3106677303C80444323 @default.
• W3106677303 hasConceptScore W3106677303C81363708 @default.
• W3106677303 hasConceptScore W3106677303C82990744 @default.
• W3106677303 hasFunder F4320321001 @default.
• W3106677303 hasFunder F4320321921 @default.
• W3106677303 hasFunder F4320335966 @default.
• W3106677303 hasLocation W31066773031 @default.
• W3106677303 hasOpenAccess W3106677303 @default.
• W3106677303 hasPrimaryLocation W31066773031 @default.
• W3106677303 hasRelatedWork W2767651786 @default.
• W3106677303 hasRelatedWork W2774550181 @default.
• W3106677303 hasRelatedWork W2900273708 @default.
• W3106677303 hasRelatedWork W290554818 @default.
• W3106677303 hasRelatedWork W2912288872 @default.
• W3106677303 hasRelatedWork W2940661641 @default.
• W3106677303 hasRelatedWork W2941723491 @default.
• W3106677303 hasRelatedWork W2954208830 @default.
• W3106677303 hasRelatedWork W3011861320 @default.

• next