Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891323887> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2891323887 abstract "Human action recognition based on skeleton sequences has wide applications in human-computer interaction and intelligent surveillance. Although previous methods have successfully applied Long Short-Term Memory(LSTM) networks to model shape evolution of human actions, it still remains a problem to efficiently recognize actions, especially for similar actions from sequential data due to the lack of the details of motion. To solve this problem, this paper presents an improved LSTM-based network to jointly learn explicit long-term shape evolution maps (SEM) and motion evolution maps (MEM). Firstly, human actions are represented as compact SEM and MEM, which mutually compensate. Secondly, these maps are jointly learned by deep LSTM networks to explore high-level temporal dependencies. Then, a weighted aggregate layer (WAL) is designed to aggregate outputs of L-STM networks cross different temporal stages. Finally, deep features of shape and motion are combined by decision level fusion. Experimental results on the currently largest NTU RGB+D dataset and public SmartHome dataset verify that our method significantly outperforms the state-of-the-arts." @default.
- W2891323887 created "2018-09-27" @default.
- W2891323887 creator A5038044561 @default.
- W2891323887 creator A5051601236 @default.
- W2891323887 creator A5057287134 @default.
- W2891323887 creator A5087148379 @default.
- W2891323887 date "2018-04-01" @default.
- W2891323887 modified "2023-09-24" @default.
- W2891323887 title "Learning Explicit Shape and Motion Evolution Maps for Skeleton-Based Human Action Recognition" @default.
- W2891323887 cites W2048821851 @default.
- W2891323887 cites W2056339039 @default.
- W2891323887 cites W2064675550 @default.
- W2891323887 cites W2214817147 @default.
- W2891323887 cites W2224196924 @default.
- W2891323887 cites W2294438834 @default.
- W2891323887 cites W2526041356 @default.
- W2891323887 cites W2593146028 @default.
- W2891323887 cites W2612707971 @default.
- W2891323887 cites W2689551733 @default.
- W2891323887 cites W2964134613 @default.
- W2891323887 cites W4230005465 @default.
- W2891323887 doi "https://doi.org/10.1109/icassp.2018.8462061" @default.
- W2891323887 hasPublicationYear "2018" @default.
- W2891323887 type Work @default.
- W2891323887 sameAs 2891323887 @default.
- W2891323887 citedByCount "10" @default.
- W2891323887 countsByYear W28913238872020 @default.
- W2891323887 countsByYear W28913238872021 @default.
- W2891323887 countsByYear W28913238872022 @default.
- W2891323887 countsByYear W28913238872023 @default.
- W2891323887 crossrefType "proceedings-article" @default.
- W2891323887 hasAuthorship W2891323887A5038044561 @default.
- W2891323887 hasAuthorship W2891323887A5051601236 @default.
- W2891323887 hasAuthorship W2891323887A5057287134 @default.
- W2891323887 hasAuthorship W2891323887A5087148379 @default.
- W2891323887 hasConcept C104114177 @default.
- W2891323887 hasConcept C108583219 @default.
- W2891323887 hasConcept C121332964 @default.
- W2891323887 hasConcept C153180895 @default.
- W2891323887 hasConcept C154945302 @default.
- W2891323887 hasConcept C159985019 @default.
- W2891323887 hasConcept C18969341 @default.
- W2891323887 hasConcept C192562407 @default.
- W2891323887 hasConcept C199360897 @default.
- W2891323887 hasConcept C2777212361 @default.
- W2891323887 hasConcept C2780791683 @default.
- W2891323887 hasConcept C2987834672 @default.
- W2891323887 hasConcept C31972630 @default.
- W2891323887 hasConcept C41008148 @default.
- W2891323887 hasConcept C4679612 @default.
- W2891323887 hasConcept C48007421 @default.
- W2891323887 hasConcept C50644808 @default.
- W2891323887 hasConcept C61797465 @default.
- W2891323887 hasConcept C62520636 @default.
- W2891323887 hasConcept C82990744 @default.
- W2891323887 hasConceptScore W2891323887C104114177 @default.
- W2891323887 hasConceptScore W2891323887C108583219 @default.
- W2891323887 hasConceptScore W2891323887C121332964 @default.
- W2891323887 hasConceptScore W2891323887C153180895 @default.
- W2891323887 hasConceptScore W2891323887C154945302 @default.
- W2891323887 hasConceptScore W2891323887C159985019 @default.
- W2891323887 hasConceptScore W2891323887C18969341 @default.
- W2891323887 hasConceptScore W2891323887C192562407 @default.
- W2891323887 hasConceptScore W2891323887C199360897 @default.
- W2891323887 hasConceptScore W2891323887C2777212361 @default.
- W2891323887 hasConceptScore W2891323887C2780791683 @default.
- W2891323887 hasConceptScore W2891323887C2987834672 @default.
- W2891323887 hasConceptScore W2891323887C31972630 @default.
- W2891323887 hasConceptScore W2891323887C41008148 @default.
- W2891323887 hasConceptScore W2891323887C4679612 @default.
- W2891323887 hasConceptScore W2891323887C48007421 @default.
- W2891323887 hasConceptScore W2891323887C50644808 @default.
- W2891323887 hasConceptScore W2891323887C61797465 @default.
- W2891323887 hasConceptScore W2891323887C62520636 @default.
- W2891323887 hasConceptScore W2891323887C82990744 @default.
- W2891323887 hasLocation W28913238871 @default.
- W2891323887 hasOpenAccess W2891323887 @default.
- W2891323887 hasPrimaryLocation W28913238871 @default.
- W2891323887 hasRelatedWork W2030131924 @default.
- W2891323887 hasRelatedWork W2096175171 @default.
- W2891323887 hasRelatedWork W2314488738 @default.
- W2891323887 hasRelatedWork W2545445363 @default.
- W2891323887 hasRelatedWork W2746445126 @default.
- W2891323887 hasRelatedWork W2997897143 @default.
- W2891323887 hasRelatedWork W4281708832 @default.
- W2891323887 hasRelatedWork W4294974964 @default.
- W2891323887 hasRelatedWork W4298053145 @default.
- W2891323887 hasRelatedWork W4321512589 @default.
- W2891323887 isParatext "false" @default.
- W2891323887 isRetracted "false" @default.
- W2891323887 magId "2891323887" @default.
- W2891323887 workType "article" @default.