FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3170431411> ?p ?o ?g. }

• W3170431411 endingPage "2331" @default.
• W3170431411 startingPage "2317" @default.
• W3170431411 abstract "In skeleton-based action recognition, graph convolutional networks (GCNs), which model human body skeletons using graphical components such as nodes and connections, have recently achieved remarkable performance. While the current state-of-the-art methods for skeleton-based action recognition usually assume that completely observed skeletons will be provided, it is problematic to realize this assumption in real-world scenarios since the captured skeletons may be incomplete or noisy. In this work, we propose a skeleton-based action recognition method that is robust to noise interference for the given skeleton features. The key insight of our approach is to train a model by maximizing the mutual information between normal and noisy skeletons using predictive coding in the latent space. We conducted comprehensive skeleton-based action recognition experiments with defective skeletons using the NTU-RGB+D and Kinetics-Skeleton datasets. The experimental results demonstrate that when the skeleton samples are noisy, our approach achieves outstanding performances compared with the existing state-of-the-art methods." @default.
• W3170431411 created "2021-06-22" @default.
• W3170431411 creator A5015974442 @default.
• W3170431411 creator A5056280822 @default.
• W3170431411 creator A5056743652 @default.
• W3170431411 date "2021-06-09" @default.
• W3170431411 modified "2023-10-12" @default.
• W3170431411 title "Predictively encoded graph convolutional network for noise-robust skeleton-based action recognition" @default.
• W3170431411 cites W1536680647 @default.
• W3170431411 cites W1926645898 @default.
• W3170431411 cites W2037034710 @default.
• W3170431411 cites W2056898157 @default.
• W3170431411 cites W2089412209 @default.
• W3170431411 cites W2112129677 @default.
• W3170431411 cites W2125337569 @default.
• W3170431411 cites W2145546283 @default.
• W3170431411 cites W2152808281 @default.
• W3170431411 cites W2157026765 @default.
• W3170431411 cites W2342662179 @default.
• W3170431411 cites W2422305492 @default.
• W3170431411 cites W2510185399 @default.
• W3170431411 cites W2548197316 @default.
• W3170431411 cites W2559085405 @default.
• W3170431411 cites W2593146028 @default.
• W3170431411 cites W2603861860 @default.
• W3170431411 cites W2607037079 @default.
• W3170431411 cites W2608988379 @default.
• W3170431411 cites W2613570903 @default.
• W3170431411 cites W2751445731 @default.
• W3170431411 cites W2798644314 @default.
• W3170431411 cites W2802979841 @default.
• W3170431411 cites W2884496896 @default.
• W3170431411 cites W2906548844 @default.
• W3170431411 cites W2940457086 @default.
• W3170431411 cites W2948058585 @default.
• W3170431411 cites W2948246283 @default.
• W3170431411 cites W2950568498 @default.
• W3170431411 cites W2963032654 @default.
• W3170431411 cites W2963076818 @default.
• W3170431411 cites W2963177347 @default.
• W3170431411 cites W2963465695 @default.
• W3170431411 cites W2963795951 @default.
• W3170431411 cites W2963881378 @default.
• W3170431411 cites W2964134613 @default.
• W3170431411 cites W2965747269 @default.
• W3170431411 cites W2981578854 @default.
• W3170431411 cites W2996835428 @default.
• W3170431411 cites W3041830016 @default.
• W3170431411 cites W3092754310 @default.
• W3170431411 cites W3098538019 @default.
• W3170431411 cites W3099014939 @default.
• W3170431411 cites W3107322323 @default.
• W3170431411 cites W3110854813 @default.
• W3170431411 cites W3123784868 @default.
• W3170431411 cites W3145385912 @default.
• W3170431411 doi "https://doi.org/10.1007/s10489-021-02487-z" @default.
• W3170431411 hasPublicationYear "2021" @default.
• W3170431411 type Work @default.
• W3170431411 sameAs 3170431411 @default.
• W3170431411 citedByCount "18" @default.
• W3170431411 countsByYear W31704314112021 @default.
• W3170431411 countsByYear W31704314112022 @default.
• W3170431411 countsByYear W31704314112023 @default.
• W3170431411 crossrefType "journal-article" @default.
• W3170431411 hasAuthorship W3170431411A5015974442 @default.
• W3170431411 hasAuthorship W3170431411A5056280822 @default.
• W3170431411 hasAuthorship W3170431411A5056743652 @default.
• W3170431411 hasBestOaLocation W31704314112 @default.
• W3170431411 hasConcept C115961682 @default.
• W3170431411 hasConcept C132525143 @default.
• W3170431411 hasConcept C153180895 @default.
• W3170431411 hasConcept C154945302 @default.
• W3170431411 hasConcept C18969341 @default.
• W3170431411 hasConcept C199360897 @default.
• W3170431411 hasConcept C2777212361 @default.
• W3170431411 hasConcept C2777846634 @default.
• W3170431411 hasConcept C2987834672 @default.
• W3170431411 hasConcept C41008148 @default.
• W3170431411 hasConcept C80444323 @default.
• W3170431411 hasConcept C81363708 @default.
• W3170431411 hasConcept C82990744 @default.
• W3170431411 hasConcept C99498987 @default.
• W3170431411 hasConceptScore W3170431411C115961682 @default.
• W3170431411 hasConceptScore W3170431411C132525143 @default.
• W3170431411 hasConceptScore W3170431411C153180895 @default.
• W3170431411 hasConceptScore W3170431411C154945302 @default.
• W3170431411 hasConceptScore W3170431411C18969341 @default.
• W3170431411 hasConceptScore W3170431411C199360897 @default.
• W3170431411 hasConceptScore W3170431411C2777212361 @default.
• W3170431411 hasConceptScore W3170431411C2777846634 @default.
• W3170431411 hasConceptScore W3170431411C2987834672 @default.
• W3170431411 hasConceptScore W3170431411C41008148 @default.
• W3170431411 hasConceptScore W3170431411C80444323 @default.
• W3170431411 hasConceptScore W3170431411C81363708 @default.
• W3170431411 hasConceptScore W3170431411C82990744 @default.
• W3170431411 hasConceptScore W3170431411C99498987 @default.
• W3170431411 hasIssue "3" @default.
• W3170431411 hasLocation W31704314111 @default.

• next