FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380051780> ?p ?o ?g. }

• W4380051780 endingPage "5414" @default.
• W4380051780 startingPage "5414" @default.
• W4380051780 abstract "Graph convolutional networks are widely used in skeleton-based action recognition because of their good fitting ability to non-Euclidean data. While conventional multi-scale temporal convolution uses several fixed-size convolution kernels or dilation rates at each layer of the network, we argue that different layers and datasets require different receptive fields. We use multi-scale adaptive convolution kernels and dilation rates to optimize traditional multi-scale temporal convolution with a simple and effective self attention mechanism, allowing different network layers to adaptively select convolution kernels of different sizes and dilation rates instead of being fixed and unchanged. Besides, the effective receptive field of the simple residual connection is not large, and there is a great deal of redundancy in the deep residual network, which will lead to the loss of context when aggregating spatio-temporal information. This article introduces a feature fusion mechanism that replaces the residual connection between initial features and temporal module outputs, effectively solving the problems of context aggregation and initial feature fusion. We propose a multi-modality adaptive feature fusion framework (MMAFF) to simultaneously increase the receptive field in both spatial and temporal dimensions. Concretely, we input the features extracted by the spatial module into the adaptive temporal fusion module to simultaneously extract multi-scale skeleton features in both spatial and temporal parts. In addition, based on the current multi-stream approach, we use the limb stream to uniformly process correlated data from multiple modalities. Extensive experiments show that our model obtains competitive results with state-of-the-art methods on the NTU-RGB+D 60 and NTU-RGB+D 120 datasets." @default.
• W4380051780 created "2023-06-10" @default.
• W4380051780 creator A5009553453 @default.
• W4380051780 creator A5011673829 @default.
• W4380051780 creator A5015680889 @default.
• W4380051780 creator A5028930572 @default.
• W4380051780 creator A5031538783 @default.
• W4380051780 creator A5042936370 @default.
• W4380051780 creator A5043738330 @default.
• W4380051780 date "2023-06-07" @default.
• W4380051780 modified "2023-09-30" @default.
• W4380051780 title "Multi-Modality Adaptive Feature Fusion Graph Convolutional Network for Skeleton-Based Action Recognition" @default.
• W4380051780 cites W1744759976 @default.
• W4380051780 cites W2593146028 @default.
• W4380051780 cites W2736334449 @default.
• W4380051780 cites W2940457086 @default.
• W4380051780 cites W2944006115 @default.
• W4380051780 cites W2948058585 @default.
• W4380051780 cites W2948246283 @default.
• W4380051780 cites W2950568498 @default.
• W4380051780 cites W2963076818 @default.
• W4380051780 cites W2964134613 @default.
• W4380051780 cites W3008798487 @default.
• W4380051780 cites W3034552520 @default.
• W4380051780 cites W3034999503 @default.
• W4380051780 cites W3035050855 @default.
• W4380051780 cites W3035225512 @default.
• W4380051780 cites W3092336341 @default.
• W4380051780 cites W3092754310 @default.
• W4380051780 cites W3093411241 @default.
• W4380051780 cites W3094897602 @default.
• W4380051780 cites W3113067059 @default.
• W4380051780 cites W3174836262 @default.
• W4380051780 cites W3185273257 @default.
• W4380051780 cites W3203634062 @default.
• W4380051780 cites W4221166048 @default.
• W4380051780 cites W4281249524 @default.
• W4380051780 cites W4296438114 @default.
• W4380051780 cites W4308497268 @default.
• W4380051780 cites W4311752814 @default.
• W4380051780 cites W4312245820 @default.
• W4380051780 cites W4312757522 @default.
• W4380051780 cites W4321769488 @default.
• W4380051780 cites W4362615253 @default.
• W4380051780 doi "https://doi.org/10.3390/s23125414" @default.
• W4380051780 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37420580" @default.
• W4380051780 hasPublicationYear "2023" @default.
• W4380051780 type Work @default.
• W4380051780 citedByCount "0" @default.
• W4380051780 crossrefType "journal-article" @default.
• W4380051780 hasAuthorship W4380051780A5009553453 @default.
• W4380051780 hasAuthorship W4380051780A5011673829 @default.
• W4380051780 hasAuthorship W4380051780A5015680889 @default.
• W4380051780 hasAuthorship W4380051780A5028930572 @default.
• W4380051780 hasAuthorship W4380051780A5031538783 @default.
• W4380051780 hasAuthorship W4380051780A5042936370 @default.
• W4380051780 hasAuthorship W4380051780A5043738330 @default.
• W4380051780 hasBestOaLocation W43800517801 @default.
• W4380051780 hasConcept C11413529 @default.
• W4380051780 hasConcept C114614502 @default.
• W4380051780 hasConcept C132525143 @default.
• W4380051780 hasConcept C138885662 @default.
• W4380051780 hasConcept C153180895 @default.
• W4380051780 hasConcept C154945302 @default.
• W4380051780 hasConcept C155512373 @default.
• W4380051780 hasConcept C2776401178 @default.
• W4380051780 hasConcept C2780757906 @default.
• W4380051780 hasConcept C33923547 @default.
• W4380051780 hasConcept C41008148 @default.
• W4380051780 hasConcept C41895202 @default.
• W4380051780 hasConcept C45347329 @default.
• W4380051780 hasConcept C50644808 @default.
• W4380051780 hasConcept C80444323 @default.
• W4380051780 hasConcept C81363708 @default.
• W4380051780 hasConceptScore W4380051780C11413529 @default.
• W4380051780 hasConceptScore W4380051780C114614502 @default.
• W4380051780 hasConceptScore W4380051780C132525143 @default.
• W4380051780 hasConceptScore W4380051780C138885662 @default.
• W4380051780 hasConceptScore W4380051780C153180895 @default.
• W4380051780 hasConceptScore W4380051780C154945302 @default.
• W4380051780 hasConceptScore W4380051780C155512373 @default.
• W4380051780 hasConceptScore W4380051780C2776401178 @default.
• W4380051780 hasConceptScore W4380051780C2780757906 @default.
• W4380051780 hasConceptScore W4380051780C33923547 @default.
• W4380051780 hasConceptScore W4380051780C41008148 @default.
• W4380051780 hasConceptScore W4380051780C41895202 @default.
• W4380051780 hasConceptScore W4380051780C45347329 @default.
• W4380051780 hasConceptScore W4380051780C50644808 @default.
• W4380051780 hasConceptScore W4380051780C80444323 @default.
• W4380051780 hasConceptScore W4380051780C81363708 @default.
• W4380051780 hasIssue "12" @default.
• W4380051780 hasLocation W43800517801 @default.
• W4380051780 hasLocation W43800517802 @default.
• W4380051780 hasOpenAccess W4380051780 @default.
• W4380051780 hasPrimaryLocation W43800517801 @default.
• W4380051780 hasRelatedWork W2295021132 @default.
• W4380051780 hasRelatedWork W2610482638 @default.
• W4380051780 hasRelatedWork W2766634277 @default.

• next