FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296474212> ?p ?o ?g. }

• W4296474212 endingPage "110" @default.
• W4296474212 startingPage "103" @default.
• W4296474212 abstract "Emotion recognition from body gestures is challenging since similar emotions can be expressed by arbitrary spatial configurations of joints, which results in relying on modeling spatial-temporal patterns from a more global level. However, most recent powerful graph convolution networks (GCNs) separate the spatial and temporal modeling into isolated processes, where GCN models spatial interactions using partially fixed adjacent matrices and 1D convolution captures temporal dynamics, which is insufficient for emotion recognition. In this work, we propose the 3D-Shift GCN, which enables interactions of joints within a spatial-temporal volume for global feature extraction. Besides, we further develop a multiscale architecture, the MS-Shift GCN, to fuse features captured under different temporal ranges for modeling richer dynamics. After conducting evaluation on two regular action recognition benchmarks and two gesture based emotion recognition datasets, the results show that the proposed method outperforms several state-of-the-art methods." @default.
• W4296474212 created "2022-09-21" @default.
• W4296474212 creator A5000239092 @default.
• W4296474212 creator A5019479187 @default.
• W4296474212 creator A5021687717 @default.
• W4296474212 creator A5061444109 @default.
• W4296474212 creator A5082301986 @default.
• W4296474212 date "2022-07-01" @default.
• W4296474212 modified "2023-10-16" @default.
• W4296474212 title "Multiscale 3D-Shift Graph Convolution Network for Emotion Recognition From Human Actions" @default.
• W4296474212 cites W1533666801 @default.
• W4296474212 cites W1587447546 @default.
• W4296474212 cites W1689644917 @default.
• W4296474212 cites W2137935458 @default.
• W4296474212 cites W2157441726 @default.
• W4296474212 cites W2306941105 @default.
• W4296474212 cites W2465165615 @default.
• W4296474212 cites W2556418146 @default.
• W4296474212 cites W2888816955 @default.
• W4296474212 cites W2940457086 @default.
• W4296474212 cites W2944006115 @default.
• W4296474212 cites W2948058585 @default.
• W4296474212 cites W2956286548 @default.
• W4296474212 cites W2963076818 @default.
• W4296474212 cites W2963465695 @default.
• W4296474212 cites W2963631961 @default.
• W4296474212 cites W2964134613 @default.
• W4296474212 cites W2978855205 @default.
• W4296474212 cites W3034999503 @default.
• W4296474212 cites W3035050855 @default.
• W4296474212 cites W3035225512 @default.
• W4296474212 cites W3123784868 @default.
• W4296474212 cites W3163767300 @default.
• W4296474212 doi "https://doi.org/10.1109/mis.2022.3147585" @default.
• W4296474212 hasPublicationYear "2022" @default.
• W4296474212 type Work @default.
• W4296474212 citedByCount "5" @default.
• W4296474212 countsByYear W42964742122022 @default.
• W4296474212 countsByYear W42964742122023 @default.
• W4296474212 crossrefType "journal-article" @default.
• W4296474212 hasAuthorship W4296474212A5000239092 @default.
• W4296474212 hasAuthorship W4296474212A5019479187 @default.
• W4296474212 hasAuthorship W4296474212A5021687717 @default.
• W4296474212 hasAuthorship W4296474212A5061444109 @default.
• W4296474212 hasAuthorship W4296474212A5082301986 @default.
• W4296474212 hasBestOaLocation W42964742122 @default.
• W4296474212 hasConcept C119599485 @default.
• W4296474212 hasConcept C127413603 @default.
• W4296474212 hasConcept C132525143 @default.
• W4296474212 hasConcept C141353440 @default.
• W4296474212 hasConcept C153180895 @default.
• W4296474212 hasConcept C154945302 @default.
• W4296474212 hasConcept C159437735 @default.
• W4296474212 hasConcept C207347870 @default.
• W4296474212 hasConcept C2777212361 @default.
• W4296474212 hasConcept C2777438025 @default.
• W4296474212 hasConcept C2987834672 @default.
• W4296474212 hasConcept C41008148 @default.
• W4296474212 hasConcept C45347329 @default.
• W4296474212 hasConcept C50644808 @default.
• W4296474212 hasConcept C52622490 @default.
• W4296474212 hasConcept C80444323 @default.
• W4296474212 hasConceptScore W4296474212C119599485 @default.
• W4296474212 hasConceptScore W4296474212C127413603 @default.
• W4296474212 hasConceptScore W4296474212C132525143 @default.
• W4296474212 hasConceptScore W4296474212C141353440 @default.
• W4296474212 hasConceptScore W4296474212C153180895 @default.
• W4296474212 hasConceptScore W4296474212C154945302 @default.
• W4296474212 hasConceptScore W4296474212C159437735 @default.
• W4296474212 hasConceptScore W4296474212C207347870 @default.
• W4296474212 hasConceptScore W4296474212C2777212361 @default.
• W4296474212 hasConceptScore W4296474212C2777438025 @default.
• W4296474212 hasConceptScore W4296474212C2987834672 @default.
• W4296474212 hasConceptScore W4296474212C41008148 @default.
• W4296474212 hasConceptScore W4296474212C45347329 @default.
• W4296474212 hasConceptScore W4296474212C50644808 @default.
• W4296474212 hasConceptScore W4296474212C52622490 @default.
• W4296474212 hasConceptScore W4296474212C80444323 @default.
• W4296474212 hasFunder F4320322411 @default.
• W4296474212 hasFunder F4320336704 @default.
• W4296474212 hasIssue "4" @default.
• W4296474212 hasLocation W42964742121 @default.
• W4296474212 hasLocation W42964742122 @default.
• W4296474212 hasOpenAccess W4296474212 @default.
• W4296474212 hasPrimaryLocation W42964742121 @default.
• W4296474212 hasRelatedWork W1728708896 @default.
• W4296474212 hasRelatedWork W2298445842 @default.
• W4296474212 hasRelatedWork W2695951553 @default.
• W4296474212 hasRelatedWork W2811390910 @default.
• W4296474212 hasRelatedWork W2998169797 @default.
• W4296474212 hasRelatedWork W3024770267 @default.
• W4296474212 hasRelatedWork W3106494386 @default.
• W4296474212 hasRelatedWork W3160300648 @default.
• W4296474212 hasRelatedWork W4293731510 @default.
• W4296474212 hasRelatedWork W4296474212 @default.
• W4296474212 hasVolume "37" @default.
• W4296474212 isParatext "false" @default.
• W4296474212 isRetracted "false" @default.

• next