Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387652107> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4387652107 endingPage "104841" @default.
- W4387652107 startingPage "104841" @default.
- W4387652107 abstract "Graph convolutional networks (GCNs) have been applied to 2D-to-3D human pose estimation (HPE) and have shown encouraging performance. However, existing GCNs model the relations between joints via individual kernels, which can be overly flexible and fail to capture common relational patterns due to the symmetric nature of the human body. Although some GCNs share kernels to capture common relations, the unified way for all neighbors limits relational diversity to some extent. In order to balance the diversity and commonality of relations, we conduct a comprehensive study of existing kernel-sharing strategies and propose a Relation-balanced Graph Convolutional Network (RbGC-Net). RbGC-Net introduces the Part-Specific Kernel-Sharing strategy (PSKS) that assigns kernels based on the semantic meanings of neighbors to establish specific relational patterns for different types of neighborhoods. Furthermore, RbGC-Net incorporates a Local–Global Feature Fusion module (LGFF) that extracts the local relations among joints and balances them with the final global relations to improve the interactions between joints. Compared with state-of-the-art methods for 3D HPE, our RbGC-Net achieves the optimal balance between model size and estimation errors. Results on two benchmark Human3.6 M and MPI-INF-3DHP datasets demonstrate the excellent performance and strong generalization ability of our pure GCN-based method." @default.
- W4387652107 created "2023-10-16" @default.
- W4387652107 creator A5010726528 @default.
- W4387652107 creator A5012301761 @default.
- W4387652107 date "2023-10-01" @default.
- W4387652107 modified "2023-10-16" @default.
- W4387652107 title "Relation-balanced graph convolutional network for 3D human pose estimation" @default.
- W4387652107 cites W2101032778 @default.
- W4387652107 cites W2123503110 @default.
- W4387652107 cites W2766703716 @default.
- W4387652107 cites W2963084622 @default.
- W4387652107 cites W3006893391 @default.
- W4387652107 cites W3165265377 @default.
- W4387652107 cites W3193806661 @default.
- W4387652107 cites W4224219693 @default.
- W4387652107 cites W4288045115 @default.
- W4387652107 cites W4321113592 @default.
- W4387652107 doi "https://doi.org/10.1016/j.imavis.2023.104841" @default.
- W4387652107 hasPublicationYear "2023" @default.
- W4387652107 type Work @default.
- W4387652107 citedByCount "0" @default.
- W4387652107 crossrefType "journal-article" @default.
- W4387652107 hasAuthorship W4387652107A5010726528 @default.
- W4387652107 hasAuthorship W4387652107A5012301761 @default.
- W4387652107 hasConcept C114614502 @default.
- W4387652107 hasConcept C119857082 @default.
- W4387652107 hasConcept C124101348 @default.
- W4387652107 hasConcept C132525143 @default.
- W4387652107 hasConcept C13280743 @default.
- W4387652107 hasConcept C134306372 @default.
- W4387652107 hasConcept C153180895 @default.
- W4387652107 hasConcept C154945302 @default.
- W4387652107 hasConcept C177148314 @default.
- W4387652107 hasConcept C185798385 @default.
- W4387652107 hasConcept C205649164 @default.
- W4387652107 hasConcept C25343380 @default.
- W4387652107 hasConcept C33923547 @default.
- W4387652107 hasConcept C41008148 @default.
- W4387652107 hasConcept C52102323 @default.
- W4387652107 hasConcept C74193536 @default.
- W4387652107 hasConcept C80444323 @default.
- W4387652107 hasConcept C81363708 @default.
- W4387652107 hasConceptScore W4387652107C114614502 @default.
- W4387652107 hasConceptScore W4387652107C119857082 @default.
- W4387652107 hasConceptScore W4387652107C124101348 @default.
- W4387652107 hasConceptScore W4387652107C132525143 @default.
- W4387652107 hasConceptScore W4387652107C13280743 @default.
- W4387652107 hasConceptScore W4387652107C134306372 @default.
- W4387652107 hasConceptScore W4387652107C153180895 @default.
- W4387652107 hasConceptScore W4387652107C154945302 @default.
- W4387652107 hasConceptScore W4387652107C177148314 @default.
- W4387652107 hasConceptScore W4387652107C185798385 @default.
- W4387652107 hasConceptScore W4387652107C205649164 @default.
- W4387652107 hasConceptScore W4387652107C25343380 @default.
- W4387652107 hasConceptScore W4387652107C33923547 @default.
- W4387652107 hasConceptScore W4387652107C41008148 @default.
- W4387652107 hasConceptScore W4387652107C52102323 @default.
- W4387652107 hasConceptScore W4387652107C74193536 @default.
- W4387652107 hasConceptScore W4387652107C80444323 @default.
- W4387652107 hasConceptScore W4387652107C81363708 @default.
- W4387652107 hasLocation W43876521071 @default.
- W4387652107 hasOpenAccess W4387652107 @default.
- W4387652107 hasPrimaryLocation W43876521071 @default.
- W4387652107 hasRelatedWork W2028665553 @default.
- W4387652107 hasRelatedWork W2086519370 @default.
- W4387652107 hasRelatedWork W2087343574 @default.
- W4387652107 hasRelatedWork W2105860728 @default.
- W4387652107 hasRelatedWork W2130974462 @default.
- W4387652107 hasRelatedWork W2378211422 @default.
- W4387652107 hasRelatedWork W2535915176 @default.
- W4387652107 hasRelatedWork W2950785639 @default.
- W4387652107 hasRelatedWork W4321353415 @default.
- W4387652107 hasRelatedWork W972276598 @default.
- W4387652107 isParatext "false" @default.
- W4387652107 isRetracted "false" @default.
- W4387652107 workType "article" @default.