Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288045765> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4288045765 endingPage "53" @default.
- W4288045765 startingPage "40" @default.
- W4288045765 abstract "Skeleton-based human action recognition has drawn more and more attention due to its easy implementation and stable application in intelligent human-robot interaction. However, most existing studies only used the skeleton data but completely ignored other image semantic information to build action recognition models, which would confuse the recognition of similar actions because of the ambiguity between skeleton data. Here, a center-connected graph convolutional network enhanced with salient image features (SIFE-CGCN) is proposed to address the problem of similar action recognition. First, a center-connected network (CGCN) is constructed to capture the small differences between similar actions through exploring the possible collaboration between all joints. Subsequently, a metric of movement changes is employed to optimally select the salient image from an action video, and then the EfficientNet is used to achieve the action semantic classification of the salient images. Finally, the recognition results of CGCN are strengthened with the classification results of salient images to further improve the recognition accuracy for similar actions. Additionally, a metric is proposed to measure the action similarity with the skeleton data, and then a similar action dataset is built. Extensive experiments on the datasets of similar action and NTU RGB + D 60/120 were conducted to verify the performance of the proposed methods. Experimental results validated the effectiveness of salient image feature enhancement and showed that the proposed SIFE-CGCN achieved the state-of-the-art performance on the similar action and NTU RGB + D 60/120 datasets." @default.
- W4288045765 created "2022-07-27" @default.
- W4288045765 creator A5004452472 @default.
- W4288045765 creator A5009013564 @default.
- W4288045765 creator A5018547551 @default.
- W4288045765 creator A5034911101 @default.
- W4288045765 creator A5055011346 @default.
- W4288045765 creator A5082265547 @default.
- W4288045765 date "2022-10-01" @default.
- W4288045765 modified "2023-10-06" @default.
- W4288045765 title "Skeleton-based similar action recognition through integrating the salient image feature into a center-connected graph convolutional network" @default.
- W4288045765 cites W2056898157 @default.
- W4288045765 cites W2081240112 @default.
- W4288045765 cites W2083572085 @default.
- W4288045765 cites W2101491865 @default.
- W4288045765 cites W2313903725 @default.
- W4288045765 cites W2593146028 @default.
- W4288045765 cites W2605847739 @default.
- W4288045765 cites W2613570903 @default.
- W4288045765 cites W2716916105 @default.
- W4288045765 cites W2767933817 @default.
- W4288045765 cites W2885940446 @default.
- W4288045765 cites W2899936784 @default.
- W4288045765 cites W2944006115 @default.
- W4288045765 cites W2950568498 @default.
- W4288045765 cites W2966210862 @default.
- W4288045765 cites W2996835428 @default.
- W4288045765 cites W3007882796 @default.
- W4288045765 cites W3093568604 @default.
- W4288045765 cites W3123784868 @default.
- W4288045765 cites W3158830199 @default.
- W4288045765 cites W4282981352 @default.
- W4288045765 doi "https://doi.org/10.1016/j.neucom.2022.07.080" @default.
- W4288045765 hasPublicationYear "2022" @default.
- W4288045765 type Work @default.
- W4288045765 citedByCount "2" @default.
- W4288045765 countsByYear W42880457652023 @default.
- W4288045765 crossrefType "journal-article" @default.
- W4288045765 hasAuthorship W4288045765A5004452472 @default.
- W4288045765 hasAuthorship W4288045765A5009013564 @default.
- W4288045765 hasAuthorship W4288045765A5018547551 @default.
- W4288045765 hasAuthorship W4288045765A5034911101 @default.
- W4288045765 hasAuthorship W4288045765A5055011346 @default.
- W4288045765 hasAuthorship W4288045765A5082265547 @default.
- W4288045765 hasConcept C115961682 @default.
- W4288045765 hasConcept C132525143 @default.
- W4288045765 hasConcept C138885662 @default.
- W4288045765 hasConcept C153180895 @default.
- W4288045765 hasConcept C154945302 @default.
- W4288045765 hasConcept C18969341 @default.
- W4288045765 hasConcept C199360897 @default.
- W4288045765 hasConcept C2776401178 @default.
- W4288045765 hasConcept C2780719617 @default.
- W4288045765 hasConcept C31972630 @default.
- W4288045765 hasConcept C41008148 @default.
- W4288045765 hasConcept C41895202 @default.
- W4288045765 hasConcept C52622490 @default.
- W4288045765 hasConcept C80444323 @default.
- W4288045765 hasConcept C81363708 @default.
- W4288045765 hasConcept C82990744 @default.
- W4288045765 hasConceptScore W4288045765C115961682 @default.
- W4288045765 hasConceptScore W4288045765C132525143 @default.
- W4288045765 hasConceptScore W4288045765C138885662 @default.
- W4288045765 hasConceptScore W4288045765C153180895 @default.
- W4288045765 hasConceptScore W4288045765C154945302 @default.
- W4288045765 hasConceptScore W4288045765C18969341 @default.
- W4288045765 hasConceptScore W4288045765C199360897 @default.
- W4288045765 hasConceptScore W4288045765C2776401178 @default.
- W4288045765 hasConceptScore W4288045765C2780719617 @default.
- W4288045765 hasConceptScore W4288045765C31972630 @default.
- W4288045765 hasConceptScore W4288045765C41008148 @default.
- W4288045765 hasConceptScore W4288045765C41895202 @default.
- W4288045765 hasConceptScore W4288045765C52622490 @default.
- W4288045765 hasConceptScore W4288045765C80444323 @default.
- W4288045765 hasConceptScore W4288045765C81363708 @default.
- W4288045765 hasConceptScore W4288045765C82990744 @default.
- W4288045765 hasFunder F4320321001 @default.
- W4288045765 hasFunder F4320326907 @default.
- W4288045765 hasFunder F4320327473 @default.
- W4288045765 hasFunder F4320335787 @default.
- W4288045765 hasLocation W42880457651 @default.
- W4288045765 hasOpenAccess W4288045765 @default.
- W4288045765 hasPrimaryLocation W42880457651 @default.
- W4288045765 hasRelatedWork W2052518016 @default.
- W4288045765 hasRelatedWork W2085956791 @default.
- W4288045765 hasRelatedWork W2283162247 @default.
- W4288045765 hasRelatedWork W2314488738 @default.
- W4288045765 hasRelatedWork W2524507886 @default.
- W4288045765 hasRelatedWork W2546942002 @default.
- W4288045765 hasRelatedWork W2771653066 @default.
- W4288045765 hasRelatedWork W2774550181 @default.
- W4288045765 hasRelatedWork W4212983513 @default.
- W4288045765 hasRelatedWork W4281689716 @default.
- W4288045765 hasVolume "507" @default.
- W4288045765 isParatext "false" @default.
- W4288045765 isRetracted "false" @default.
- W4288045765 workType "article" @default.