Matches in SemOpenAlex for { <https://semopenalex.org/work/W3157449430> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3157449430 endingPage "16191" @default.
- W3157449430 startingPage "16183" @default.
- W3157449430 abstract "The emergence of low-cost depth sensors opens up new potentials for skeleton-based human action recognition. The recent methods for this task have made significant progress by incorporating graph convolution. However, they (1) have limitations in modeling the complex and variable temporal dynamics, and (2) cannot maximize the complementarity of the spatial and temporal features. Besides, (3) the loss function of these methods has an inherent weakness in optimizing the intraclass compactness. To this end, we propose a pyramidal graph convolutional network (PY-GCN) in this paper. Specifically, (1) an effective yet efficient single-oriented pyramidal convolution is proposed. It involves multiple kernels with varying sizes and depths that are capable of capturing different levels of the temporal dynamics at multiple scales. (2) A pseudo-two-stream structure for the basic block of the network is proposed to comprehensively aggregate discriminative cross-spatiotemporal features. Moreover, (3) a pairwise Gaussian loss together with the cross-entropy loss is introduced to the model, which can focus on both intraclass compactness and interclass separability. Our PY-GCN achieves state-of-the-art performance on three challenging large-scale datasets." @default.
- W3157449430 created "2021-05-10" @default.
- W3157449430 creator A5064272196 @default.
- W3157449430 creator A5069549212 @default.
- W3157449430 creator A5071710737 @default.
- W3157449430 creator A5075167001 @default.
- W3157449430 creator A5075882540 @default.
- W3157449430 creator A5080549930 @default.
- W3157449430 date "2021-07-15" @default.
- W3157449430 modified "2023-10-14" @default.
- W3157449430 title "Pyramidal Graph Convolutional Network for Skeleton-Based Human Action Recognition" @default.
- W3157449430 cites W2194775991 @default.
- W3157449430 cites W2793547936 @default.
- W3157449430 cites W2799211965 @default.
- W3157449430 cites W2902073357 @default.
- W3157449430 cites W2940457086 @default.
- W3157449430 cites W2944006115 @default.
- W3157449430 cites W2946539594 @default.
- W3157449430 cites W2948058585 @default.
- W3157449430 cites W2963369114 @default.
- W3157449430 cites W2964347220 @default.
- W3157449430 cites W2990525852 @default.
- W3157449430 cites W2996835428 @default.
- W3157449430 cites W2998586455 @default.
- W3157449430 cites W3022453529 @default.
- W3157449430 cites W3028433894 @default.
- W3157449430 cites W3034999503 @default.
- W3157449430 cites W3035050855 @default.
- W3157449430 cites W3035149912 @default.
- W3157449430 cites W3040842087 @default.
- W3157449430 cites W3043878998 @default.
- W3157449430 cites W3081276604 @default.
- W3157449430 cites W3086043674 @default.
- W3157449430 cites W3092336341 @default.
- W3157449430 cites W3123784868 @default.
- W3157449430 doi "https://doi.org/10.1109/jsen.2021.3075722" @default.
- W3157449430 hasPublicationYear "2021" @default.
- W3157449430 type Work @default.
- W3157449430 sameAs 3157449430 @default.
- W3157449430 citedByCount "5" @default.
- W3157449430 countsByYear W31574494302022 @default.
- W3157449430 countsByYear W31574494302023 @default.
- W3157449430 crossrefType "journal-article" @default.
- W3157449430 hasAuthorship W3157449430A5064272196 @default.
- W3157449430 hasAuthorship W3157449430A5069549212 @default.
- W3157449430 hasAuthorship W3157449430A5071710737 @default.
- W3157449430 hasAuthorship W3157449430A5075167001 @default.
- W3157449430 hasAuthorship W3157449430A5075882540 @default.
- W3157449430 hasAuthorship W3157449430A5080549930 @default.
- W3157449430 hasConcept C132525143 @default.
- W3157449430 hasConcept C153180895 @default.
- W3157449430 hasConcept C154945302 @default.
- W3157449430 hasConcept C184898388 @default.
- W3157449430 hasConcept C41008148 @default.
- W3157449430 hasConcept C45347329 @default.
- W3157449430 hasConcept C50644808 @default.
- W3157449430 hasConcept C80444323 @default.
- W3157449430 hasConcept C81363708 @default.
- W3157449430 hasConcept C97931131 @default.
- W3157449430 hasConceptScore W3157449430C132525143 @default.
- W3157449430 hasConceptScore W3157449430C153180895 @default.
- W3157449430 hasConceptScore W3157449430C154945302 @default.
- W3157449430 hasConceptScore W3157449430C184898388 @default.
- W3157449430 hasConceptScore W3157449430C41008148 @default.
- W3157449430 hasConceptScore W3157449430C45347329 @default.
- W3157449430 hasConceptScore W3157449430C50644808 @default.
- W3157449430 hasConceptScore W3157449430C80444323 @default.
- W3157449430 hasConceptScore W3157449430C81363708 @default.
- W3157449430 hasConceptScore W3157449430C97931131 @default.
- W3157449430 hasFunder F4320321001 @default.
- W3157449430 hasFunder F4320335440 @default.
- W3157449430 hasIssue "14" @default.
- W3157449430 hasLocation W31574494301 @default.
- W3157449430 hasOpenAccess W3157449430 @default.
- W3157449430 hasPrimaryLocation W31574494301 @default.
- W3157449430 hasRelatedWork W2024160000 @default.
- W3157449430 hasRelatedWork W2061273563 @default.
- W3157449430 hasRelatedWork W2285052147 @default.
- W3157449430 hasRelatedWork W2729514902 @default.
- W3157449430 hasRelatedWork W2743258233 @default.
- W3157449430 hasRelatedWork W2773500201 @default.
- W3157449430 hasRelatedWork W2901662007 @default.
- W3157449430 hasRelatedWork W2998168123 @default.
- W3157449430 hasRelatedWork W4287995534 @default.
- W3157449430 hasRelatedWork W4319301798 @default.
- W3157449430 hasVolume "21" @default.
- W3157449430 isParatext "false" @default.
- W3157449430 isRetracted "false" @default.
- W3157449430 magId "3157449430" @default.
- W3157449430 workType "article" @default.