Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200475926> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3200475926 abstract "In recent years, graph convolutional neural network (GCNN) has achieved the most advanced results in skeleton action recognition tasks. However, existing models mainly focus on extracting local information from joint-level and part-level, but ignore the global information of frame-level and the relevance between multiple levels, which lead to the loss of hierarchical information. Moreover, these models consider the non-physical connection relationship between nodes but neglect the dependence between body parts. The lose of topology information directly results in poor model performance. In this paper, we propose a structure-aware multi-scale hierarchical graph convolutional network (SAMS-HGCN) model, which includes two modules: a structure-aware hierarchical graph pooling block (SA-HGP Block) and a multi-scale fusion module (MSF module). Specifically, SA-HGP Block establishes a hierarchical network to capture the topological information of multiple levels by using the hierarchical graph pooling (HGP) operation and model the dependence among parts via the structure-aware learning (SA Learning) operation. MSF module fuses information of different scales in each level to obtain multi-scale global structural information. Experiments show that our method achieves comparable performances to state-of-the-art methods on NTU-RGB+D and Kinetics-Skeleton datasets." @default.
- W3200475926 created "2021-09-27" @default.
- W3200475926 creator A5014264919 @default.
- W3200475926 creator A5016915362 @default.
- W3200475926 creator A5035265607 @default.
- W3200475926 creator A5046299375 @default.
- W3200475926 creator A5063358801 @default.
- W3200475926 creator A5071560359 @default.
- W3200475926 date "2021-01-01" @default.
- W3200475926 modified "2023-10-03" @default.
- W3200475926 title "Structure-Aware Multi-scale Hierarchical Graph Convolutional Network for Skeleton Action Recognition" @default.
- W3200475926 cites W2038746778 @default.
- W3200475926 cites W2048821851 @default.
- W3200475926 cites W2056339039 @default.
- W3200475926 cites W2056898157 @default.
- W3200475926 cites W2224196924 @default.
- W3200475926 cites W2510185399 @default.
- W3200475926 cites W2593146028 @default.
- W3200475926 cites W2613570903 @default.
- W3200475926 cites W2791526950 @default.
- W3200475926 cites W2802979841 @default.
- W3200475926 cites W2940457086 @default.
- W3200475926 cites W2948058585 @default.
- W3200475926 cites W2948246283 @default.
- W3200475926 cites W2963369114 @default.
- W3200475926 cites W2964134613 @default.
- W3200475926 cites W2981341885 @default.
- W3200475926 cites W3035225512 @default.
- W3200475926 cites W3098538019 @default.
- W3200475926 cites W3119819302 @default.
- W3200475926 cites W577373822 @default.
- W3200475926 doi "https://doi.org/10.1007/978-3-030-86365-4_24" @default.
- W3200475926 hasPublicationYear "2021" @default.
- W3200475926 type Work @default.
- W3200475926 sameAs 3200475926 @default.
- W3200475926 citedByCount "1" @default.
- W3200475926 crossrefType "book-chapter" @default.
- W3200475926 hasAuthorship W3200475926A5014264919 @default.
- W3200475926 hasAuthorship W3200475926A5016915362 @default.
- W3200475926 hasAuthorship W3200475926A5035265607 @default.
- W3200475926 hasAuthorship W3200475926A5046299375 @default.
- W3200475926 hasAuthorship W3200475926A5063358801 @default.
- W3200475926 hasAuthorship W3200475926A5071560359 @default.
- W3200475926 hasConcept C132525143 @default.
- W3200475926 hasConcept C153180895 @default.
- W3200475926 hasConcept C154945302 @default.
- W3200475926 hasConcept C2524010 @default.
- W3200475926 hasConcept C2777210771 @default.
- W3200475926 hasConcept C33923547 @default.
- W3200475926 hasConcept C41008148 @default.
- W3200475926 hasConcept C59404180 @default.
- W3200475926 hasConcept C70437156 @default.
- W3200475926 hasConcept C80444323 @default.
- W3200475926 hasConcept C81363708 @default.
- W3200475926 hasConceptScore W3200475926C132525143 @default.
- W3200475926 hasConceptScore W3200475926C153180895 @default.
- W3200475926 hasConceptScore W3200475926C154945302 @default.
- W3200475926 hasConceptScore W3200475926C2524010 @default.
- W3200475926 hasConceptScore W3200475926C2777210771 @default.
- W3200475926 hasConceptScore W3200475926C33923547 @default.
- W3200475926 hasConceptScore W3200475926C41008148 @default.
- W3200475926 hasConceptScore W3200475926C59404180 @default.
- W3200475926 hasConceptScore W3200475926C70437156 @default.
- W3200475926 hasConceptScore W3200475926C80444323 @default.
- W3200475926 hasConceptScore W3200475926C81363708 @default.
- W3200475926 hasLocation W32004759261 @default.
- W3200475926 hasOpenAccess W3200475926 @default.
- W3200475926 hasPrimaryLocation W32004759261 @default.
- W3200475926 hasRelatedWork W10202958 @default.
- W3200475926 hasRelatedWork W11644230 @default.
- W3200475926 hasRelatedWork W12433487 @default.
- W3200475926 hasRelatedWork W12712126 @default.
- W3200475926 hasRelatedWork W13426426 @default.
- W3200475926 hasRelatedWork W3845813 @default.
- W3200475926 hasRelatedWork W7585623 @default.
- W3200475926 hasRelatedWork W7842670 @default.
- W3200475926 hasRelatedWork W8521998 @default.
- W3200475926 hasRelatedWork W9448574 @default.
- W3200475926 isParatext "false" @default.
- W3200475926 isRetracted "false" @default.
- W3200475926 magId "3200475926" @default.
- W3200475926 workType "book-chapter" @default.