Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323346084> ?p ?o ?g. }
- W4323346084 endingPage "20485" @default.
- W4323346084 startingPage "20478" @default.
- W4323346084 abstract "With the extraordinary ability by representing human body structure as a spatial graph, graph convolution networks (GCNs) have progressed much in skeleton-based action recognition. However, these methods usually use a predefined graph to represent human body structure, which is limited to 1-hop neighborhood with fixed weights. To handle these limitations, we propose a fully attentional network (FAN). It dynamically computes the edge weights for each input sample between graph nodes, thus avoiding the predefined fixed weights. Besides, it could attend to distant nodes by calculating their edge weights based on their similarities, thus avoiding the limited spatial receptive field. As an effective feature extractor, FAN achieves new state-of-the-art accuracy on three large-scale datasets, i.e., NTU RGB+D 60, NTU RGB+D 120 and Kinetics Skeleton 400. Visualizations are given to verify that FAN could dynamically emphasize the graph nodes that are important in expressing an action." @default.
- W4323346084 created "2023-03-08" @default.
- W4323346084 creator A5045909640 @default.
- W4323346084 creator A5047148485 @default.
- W4323346084 date "2023-01-01" @default.
- W4323346084 modified "2023-09-25" @default.
- W4323346084 title "Fully Attentional Network for Skeleton-Based Action Recognition" @default.
- W4323346084 cites W2048821851 @default.
- W4323346084 cites W2143267104 @default.
- W4323346084 cites W2194775991 @default.
- W4323346084 cites W2255466643 @default.
- W4323346084 cites W2267186426 @default.
- W4323346084 cites W2507009361 @default.
- W4323346084 cites W2510185399 @default.
- W4323346084 cites W2559085405 @default.
- W4323346084 cites W2603861860 @default.
- W4323346084 cites W2783192928 @default.
- W4323346084 cites W2802979841 @default.
- W4323346084 cites W2940457086 @default.
- W4323346084 cites W2944006115 @default.
- W4323346084 cites W2948058585 @default.
- W4323346084 cites W2948246283 @default.
- W4323346084 cites W2963076818 @default.
- W4323346084 cites W2963091558 @default.
- W4323346084 cites W2963369114 @default.
- W4323346084 cites W2963465695 @default.
- W4323346084 cites W2963524571 @default.
- W4323346084 cites W2963781481 @default.
- W4323346084 cites W2964134613 @default.
- W4323346084 cites W2964347220 @default.
- W4323346084 cites W2981341885 @default.
- W4323346084 cites W2996835428 @default.
- W4323346084 cites W3029824220 @default.
- W4323346084 cites W3034999503 @default.
- W4323346084 cites W3035050855 @default.
- W4323346084 cites W3035225512 @default.
- W4323346084 cites W3040622976 @default.
- W4323346084 cites W3092336341 @default.
- W4323346084 cites W3092754310 @default.
- W4323346084 cites W3093411241 @default.
- W4323346084 cites W3097525302 @default.
- W4323346084 cites W3098538019 @default.
- W4323346084 cites W3107940523 @default.
- W4323346084 cites W3108496296 @default.
- W4323346084 cites W3138697035 @default.
- W4323346084 cites W3174053790 @default.
- W4323346084 cites W3174836262 @default.
- W4323346084 cites W3194512065 @default.
- W4323346084 cites W3203227473 @default.
- W4323346084 cites W3203514840 @default.
- W4323346084 cites W4200633254 @default.
- W4323346084 doi "https://doi.org/10.1109/access.2023.3247840" @default.
- W4323346084 hasPublicationYear "2023" @default.
- W4323346084 type Work @default.
- W4323346084 citedByCount "0" @default.
- W4323346084 crossrefType "journal-article" @default.
- W4323346084 hasAuthorship W4323346084A5045909640 @default.
- W4323346084 hasAuthorship W4323346084A5047148485 @default.
- W4323346084 hasBestOaLocation W43233460841 @default.
- W4323346084 hasConcept C117978034 @default.
- W4323346084 hasConcept C127413603 @default.
- W4323346084 hasConcept C132525143 @default.
- W4323346084 hasConcept C153180895 @default.
- W4323346084 hasConcept C154945302 @default.
- W4323346084 hasConcept C21880701 @default.
- W4323346084 hasConcept C2777212361 @default.
- W4323346084 hasConcept C2987834672 @default.
- W4323346084 hasConcept C31972630 @default.
- W4323346084 hasConcept C41008148 @default.
- W4323346084 hasConcept C80444323 @default.
- W4323346084 hasConcept C82990744 @default.
- W4323346084 hasConceptScore W4323346084C117978034 @default.
- W4323346084 hasConceptScore W4323346084C127413603 @default.
- W4323346084 hasConceptScore W4323346084C132525143 @default.
- W4323346084 hasConceptScore W4323346084C153180895 @default.
- W4323346084 hasConceptScore W4323346084C154945302 @default.
- W4323346084 hasConceptScore W4323346084C21880701 @default.
- W4323346084 hasConceptScore W4323346084C2777212361 @default.
- W4323346084 hasConceptScore W4323346084C2987834672 @default.
- W4323346084 hasConceptScore W4323346084C31972630 @default.
- W4323346084 hasConceptScore W4323346084C41008148 @default.
- W4323346084 hasConceptScore W4323346084C80444323 @default.
- W4323346084 hasConceptScore W4323346084C82990744 @default.
- W4323346084 hasLocation W43233460841 @default.
- W4323346084 hasOpenAccess W4323346084 @default.
- W4323346084 hasPrimaryLocation W43233460841 @default.
- W4323346084 hasRelatedWork W2052518016 @default.
- W4323346084 hasRelatedWork W2081022503 @default.
- W4323346084 hasRelatedWork W2085956791 @default.
- W4323346084 hasRelatedWork W2283162247 @default.
- W4323346084 hasRelatedWork W2314488738 @default.
- W4323346084 hasRelatedWork W2524507886 @default.
- W4323346084 hasRelatedWork W2767823485 @default.
- W4323346084 hasRelatedWork W2771653066 @default.
- W4323346084 hasRelatedWork W2901949253 @default.
- W4323346084 hasRelatedWork W4212983513 @default.
- W4323346084 hasVolume "11" @default.
- W4323346084 isParatext "false" @default.