Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897591275> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2897591275 abstract "It remains a challenge to extract spatial-temporal information from skeleton sequences for 3D human action recognition. Although most recent action recognition methods based on Recurrent Neural Networks (RNN) have achieved outstanding performance, one of the shortcomings of these methods is the tendency to overemphasize the temporal information. Since 3D Convolutional Neural Networks(3D CNN) can simultaneously learn features from both spatial and temporal dimensions through capturing correlations among three-dimensional signals, this paper proposes a novel two-stream model using 3D CNN. To our best knowledge, this is the first attempt to use 3D CNN in the field of skeleton-based action recognition. Our method consists of three stages. First, skeleton joints are mapped into a 3D coordinate space to encode the spatial and temporal information. Second, 3D CNN models are separately employed to extract deep features from both spatial and temporal stream. Third, to enhance the ability of discriminative features to capture global relationships, we extend each stream into multi-temporal version. Extensive experiments on the large-scale NTU RGB-D dataset and the public SmartHome dataset demonstrate that our method outperforms most of RNN-based methods, which verify the complementary property between spatial and temporal information and the robustness to noise." @default.
- W2897591275 created "2018-10-26" @default.
- W2897591275 creator A5051601236 @default.
- W2897591275 creator A5057287134 @default.
- W2897591275 creator A5087148379 @default.
- W2897591275 date "2018-07-01" @default.
- W2897591275 modified "2023-09-25" @default.
- W2897591275 title "Skeleton-Based Human Action Recognition Using Spatial Temporal 3D Convolutional Neural Networks" @default.
- W2897591275 cites W1522734439 @default.
- W2897591275 cites W1943054406 @default.
- W2897591275 cites W1983364832 @default.
- W2897591275 cites W2007057255 @default.
- W2897591275 cites W2021150171 @default.
- W2897591275 cites W2048821851 @default.
- W2897591275 cites W2143612262 @default.
- W2897591275 cites W2144499799 @default.
- W2897591275 cites W2211722331 @default.
- W2897591275 cites W2214817147 @default.
- W2897591275 cites W2261262392 @default.
- W2897591275 cites W2415469094 @default.
- W2897591275 cites W2593146028 @default.
- W2897591275 cites W2792370642 @default.
- W2897591275 cites W2964134613 @default.
- W2897591275 doi "https://doi.org/10.1109/icme.2018.8486566" @default.
- W2897591275 hasPublicationYear "2018" @default.
- W2897591275 type Work @default.
- W2897591275 sameAs 2897591275 @default.
- W2897591275 citedByCount "17" @default.
- W2897591275 countsByYear W28975912752018 @default.
- W2897591275 countsByYear W28975912752019 @default.
- W2897591275 countsByYear W28975912752020 @default.
- W2897591275 countsByYear W28975912752021 @default.
- W2897591275 countsByYear W28975912752022 @default.
- W2897591275 countsByYear W28975912752023 @default.
- W2897591275 crossrefType "proceedings-article" @default.
- W2897591275 hasAuthorship W2897591275A5051601236 @default.
- W2897591275 hasAuthorship W2897591275A5057287134 @default.
- W2897591275 hasAuthorship W2897591275A5087148379 @default.
- W2897591275 hasConcept C104317684 @default.
- W2897591275 hasConcept C105795698 @default.
- W2897591275 hasConcept C108583219 @default.
- W2897591275 hasConcept C153180895 @default.
- W2897591275 hasConcept C154945302 @default.
- W2897591275 hasConcept C159620131 @default.
- W2897591275 hasConcept C185592680 @default.
- W2897591275 hasConcept C2777212361 @default.
- W2897591275 hasConcept C2987834672 @default.
- W2897591275 hasConcept C31972630 @default.
- W2897591275 hasConcept C33923547 @default.
- W2897591275 hasConcept C41008148 @default.
- W2897591275 hasConcept C55493867 @default.
- W2897591275 hasConcept C63479239 @default.
- W2897591275 hasConcept C66746571 @default.
- W2897591275 hasConcept C81363708 @default.
- W2897591275 hasConcept C82990744 @default.
- W2897591275 hasConcept C97931131 @default.
- W2897591275 hasConceptScore W2897591275C104317684 @default.
- W2897591275 hasConceptScore W2897591275C105795698 @default.
- W2897591275 hasConceptScore W2897591275C108583219 @default.
- W2897591275 hasConceptScore W2897591275C153180895 @default.
- W2897591275 hasConceptScore W2897591275C154945302 @default.
- W2897591275 hasConceptScore W2897591275C159620131 @default.
- W2897591275 hasConceptScore W2897591275C185592680 @default.
- W2897591275 hasConceptScore W2897591275C2777212361 @default.
- W2897591275 hasConceptScore W2897591275C2987834672 @default.
- W2897591275 hasConceptScore W2897591275C31972630 @default.
- W2897591275 hasConceptScore W2897591275C33923547 @default.
- W2897591275 hasConceptScore W2897591275C41008148 @default.
- W2897591275 hasConceptScore W2897591275C55493867 @default.
- W2897591275 hasConceptScore W2897591275C63479239 @default.
- W2897591275 hasConceptScore W2897591275C66746571 @default.
- W2897591275 hasConceptScore W2897591275C81363708 @default.
- W2897591275 hasConceptScore W2897591275C82990744 @default.
- W2897591275 hasConceptScore W2897591275C97931131 @default.
- W2897591275 hasLocation W28975912751 @default.
- W2897591275 hasOpenAccess W2897591275 @default.
- W2897591275 hasPrimaryLocation W28975912751 @default.
- W2897591275 hasRelatedWork W2614114106 @default.
- W2897591275 hasRelatedWork W2738221750 @default.
- W2897591275 hasRelatedWork W2791238083 @default.
- W2897591275 hasRelatedWork W2897591275 @default.
- W2897591275 hasRelatedWork W2905846897 @default.
- W2897591275 hasRelatedWork W2912805284 @default.
- W2897591275 hasRelatedWork W2963480192 @default.
- W2897591275 hasRelatedWork W2996522231 @default.
- W2897591275 hasRelatedWork W3103858256 @default.
- W2897591275 hasRelatedWork W4287995619 @default.
- W2897591275 isParatext "false" @default.
- W2897591275 isRetracted "false" @default.
- W2897591275 magId "2897591275" @default.
- W2897591275 workType "article" @default.