FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285597462> ?p ?o ?g. }

• W4285597462 endingPage "205" @default.
• W4285597462 startingPage "187" @default.
• W4285597462 abstract "3D skeleton data has been widely used in action recognition as the skeleton-based method has achieved good performance in complex dynamic environments. The rise of spatio-temporal graph convolutions has attracted much attention to use graph convolution to extract spatial and temporal features together in the field of skeleton-based action recognition. However, due to the huge difference in the focus of spatial and temporal features, it is difficult to improve the efficiency of extracting the spatiotemporal features. In this paper, we propose a channel attention and multi-scale neural network (CA-MSN) for skeleton-based action recognition with a series of spatio-temporal extraction modules. We exploit the relationship of body joints hierarchically through two modules, i.e., a spatial module which uses the residual GCN network with the channel attention block to extract the high-level spatial features, and a temporal module which uses the multi-scale TCN network to extract the temporal features at different scales. We perform extensive experiments on both the NTU-RGBD60 and NTU-RGBD120 datasets to verify the effectiveness of our network. The comparison results show that our method achieves the state-of-the-art performance with the competitive computing speed. In order to test the application effect of our CA-MSN model, we design a multi-task tandem network consisting of 2D pose estimation, 2D to 3D pose regression and skeleton action recognition model. The end-to-end (RGB video-to-action type) recognition effect is demonstrated. The code is available at https://github.com/Rh-Dang/CA-MSN-action-recognition.git." @default.
• W4285597462 created "2022-07-16" @default.
• W4285597462 creator A5019056174 @default.
• W4285597462 creator A5020099966 @default.
• W4285597462 creator A5037285766 @default.
• W4285597462 creator A5073789459 @default.
• W4285597462 date "2022-09-05" @default.
• W4285597462 modified "2023-10-01" @default.
• W4285597462 title "Channel attention and multi-scale graph neural networks for skeleton-based action recognition" @default.
• W4285597462 cites W2004149082 @default.
• W4285597462 cites W2067288219 @default.
• W4285597462 cites W2096214539 @default.
• W4285597462 cites W2097117768 @default.
• W4285597462 cites W2101032778 @default.
• W4285597462 cites W2510185399 @default.
• W4285597462 cites W2520707372 @default.
• W4285597462 cites W2559085405 @default.
• W4285597462 cites W2593146028 @default.
• W4285597462 cites W2603861860 @default.
• W4285597462 cites W2606294640 @default.
• W4285597462 cites W2613570903 @default.
• W4285597462 cites W2752782242 @default.
• W4285597462 cites W2778523960 @default.
• W4285597462 cites W2793547936 @default.
• W4285597462 cites W2802979841 @default.
• W4285597462 cites W2884585870 @default.
• W4285597462 cites W2889041463 @default.
• W4285597462 cites W2905571172 @default.
• W4285597462 cites W2922509574 @default.
• W4285597462 cites W2940457086 @default.
• W4285597462 cites W2944006115 @default.
• W4285597462 cites W2948058585 @default.
• W4285597462 cites W2948246283 @default.
• W4285597462 cites W2950568498 @default.
• W4285597462 cites W2952587893 @default.
• W4285597462 cites W2963076818 @default.
• W4285597462 cites W2963282966 @default.
• W4285597462 cites W2963465695 @default.
• W4285597462 cites W2963591054 @default.
• W4285597462 cites W2964097678 @default.
• W4285597462 cites W2964134613 @default.
• W4285597462 cites W2988630963 @default.
• W4285597462 cites W2990152177 @default.
• W4285597462 cites W2990525852 @default.
• W4285597462 cites W2991376513 @default.
• W4285597462 cites W2991583626 @default.
• W4285597462 cites W2993496908 @default.
• W4285597462 cites W2996835428 @default.
• W4285597462 cites W3034572008 @default.
• W4285597462 cites W3034768625 @default.
• W4285597462 cites W3034999503 @default.
• W4285597462 cites W3035050855 @default.
• W4285597462 cites W3035149912 @default.
• W4285597462 cites W3035225512 @default.
• W4285597462 cites W3035545045 @default.
• W4285597462 cites W3092654784 @default.
• W4285597462 cites W3092754310 @default.
• W4285597462 cites W3093411241 @default.
• W4285597462 cites W3098538019 @default.
• W4285597462 cites W3098612954 @default.
• W4285597462 cites W3099014939 @default.
• W4285597462 cites W3119171349 @default.
• W4285597462 cites W3119584695 @default.
• W4285597462 cites W3138121279 @default.
• W4285597462 doi "https://doi.org/10.3233/aic-210250" @default.
• W4285597462 hasPublicationYear "2022" @default.
• W4285597462 type Work @default.
• W4285597462 citedByCount "2" @default.
• W4285597462 countsByYear W42855974622023 @default.
• W4285597462 crossrefType "journal-article" @default.
• W4285597462 hasAuthorship W4285597462A5019056174 @default.
• W4285597462 hasAuthorship W4285597462A5020099966 @default.
• W4285597462 hasAuthorship W4285597462A5037285766 @default.
• W4285597462 hasAuthorship W4285597462A5073789459 @default.
• W4285597462 hasConcept C11413529 @default.
• W4285597462 hasConcept C132525143 @default.
• W4285597462 hasConcept C153180895 @default.
• W4285597462 hasConcept C154945302 @default.
• W4285597462 hasConcept C155512373 @default.
• W4285597462 hasConcept C18969341 @default.
• W4285597462 hasConcept C199360897 @default.
• W4285597462 hasConcept C2777212361 @default.
• W4285597462 hasConcept C2987834672 @default.
• W4285597462 hasConcept C41008148 @default.
• W4285597462 hasConcept C45347329 @default.
• W4285597462 hasConcept C50644808 @default.
• W4285597462 hasConcept C52622490 @default.
• W4285597462 hasConcept C80444323 @default.
• W4285597462 hasConcept C81363708 @default.
• W4285597462 hasConcept C82990744 @default.
• W4285597462 hasConceptScore W4285597462C11413529 @default.
• W4285597462 hasConceptScore W4285597462C132525143 @default.
• W4285597462 hasConceptScore W4285597462C153180895 @default.
• W4285597462 hasConceptScore W4285597462C154945302 @default.
• W4285597462 hasConceptScore W4285597462C155512373 @default.
• W4285597462 hasConceptScore W4285597462C18969341 @default.
• W4285597462 hasConceptScore W4285597462C199360897 @default.
• W4285597462 hasConceptScore W4285597462C2777212361 @default.

• next