Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387448185> ?p ?o ?g. }
- W4387448185 endingPage "8" @default.
- W4387448185 startingPage "1" @default.
- W4387448185 abstract "Skeleton-based gesture recognition has attracted extensive attention and has made great progress. However, mainstream methods generally treat all frames as equally important, which may limit performance, especially when dealing with high inter-class variance in gesture. To tackle this issue, we propose an approach that models a Markov decision process to identify keyframes while discarding irrelevant ones. This article proposes a deep reinforcement learning double-feature double-motion network comprising two main components: a baseline gesture recognition model and a frame selection network. These two components mutually influence each other, resulting in enhanced overall performance. Following the evaluation of the SHREC-17 and F-PHAB datasets, our proposed method demonstrates superior performance. Find our code at <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>https://github.com/Voldaf/DRL-DDNet</uri> ." @default.
- W4387448185 created "2023-10-10" @default.
- W4387448185 creator A5014295488 @default.
- W4387448185 creator A5016072306 @default.
- W4387448185 creator A5018582701 @default.
- W4387448185 creator A5043329212 @default.
- W4387448185 creator A5085661886 @default.
- W4387448185 date "2023-01-01" @default.
- W4387448185 modified "2023-10-18" @default.
- W4387448185 title "Keyframe Selection Via Deep Reinforcement Learning for Skeleton-Based Gesture Recognition" @default.
- W4387448185 cites W1522734439 @default.
- W4387448185 cites W1979378996 @default.
- W4387448185 cites W2145339207 @default.
- W4387448185 cites W2194775991 @default.
- W4387448185 cites W2224196924 @default.
- W4387448185 cites W2467634805 @default.
- W4387448185 cites W2593146028 @default.
- W4387448185 cites W2605111198 @default.
- W4387448185 cites W2605973302 @default.
- W4387448185 cites W2606294640 @default.
- W4387448185 cites W2736334449 @default.
- W4387448185 cites W2777985171 @default.
- W4387448185 cites W2798644314 @default.
- W4387448185 cites W2883429621 @default.
- W4387448185 cites W2905342581 @default.
- W4387448185 cites W2910217813 @default.
- W4387448185 cites W2914992758 @default.
- W4387448185 cites W2951019013 @default.
- W4387448185 cites W2963457877 @default.
- W4387448185 cites W2999237480 @default.
- W4387448185 cites W3009843393 @default.
- W4387448185 cites W3010010212 @default.
- W4387448185 cites W3035648302 @default.
- W4387448185 cites W3093657173 @default.
- W4387448185 cites W3103643891 @default.
- W4387448185 cites W3173964191 @default.
- W4387448185 cites W3183211010 @default.
- W4387448185 cites W3185273257 @default.
- W4387448185 cites W3187113103 @default.
- W4387448185 cites W3192262009 @default.
- W4387448185 cites W4210912956 @default.
- W4387448185 cites W4240042586 @default.
- W4387448185 doi "https://doi.org/10.1109/lra.2023.3322645" @default.
- W4387448185 hasPublicationYear "2023" @default.
- W4387448185 type Work @default.
- W4387448185 citedByCount "0" @default.
- W4387448185 crossrefType "journal-article" @default.
- W4387448185 hasAuthorship W4387448185A5014295488 @default.
- W4387448185 hasAuthorship W4387448185A5016072306 @default.
- W4387448185 hasAuthorship W4387448185A5018582701 @default.
- W4387448185 hasAuthorship W4387448185A5043329212 @default.
- W4387448185 hasAuthorship W4387448185A5085661886 @default.
- W4387448185 hasConcept C119857082 @default.
- W4387448185 hasConcept C126042441 @default.
- W4387448185 hasConcept C138885662 @default.
- W4387448185 hasConcept C153180895 @default.
- W4387448185 hasConcept C154945302 @default.
- W4387448185 hasConcept C177264268 @default.
- W4387448185 hasConcept C18969341 @default.
- W4387448185 hasConcept C199360897 @default.
- W4387448185 hasConcept C207347870 @default.
- W4387448185 hasConcept C2776401178 @default.
- W4387448185 hasConcept C2776760102 @default.
- W4387448185 hasConcept C2777212361 @default.
- W4387448185 hasConcept C41008148 @default.
- W4387448185 hasConcept C41895202 @default.
- W4387448185 hasConcept C76155785 @default.
- W4387448185 hasConcept C81917197 @default.
- W4387448185 hasConcept C97541855 @default.
- W4387448185 hasConcept C98045186 @default.
- W4387448185 hasConceptScore W4387448185C119857082 @default.
- W4387448185 hasConceptScore W4387448185C126042441 @default.
- W4387448185 hasConceptScore W4387448185C138885662 @default.
- W4387448185 hasConceptScore W4387448185C153180895 @default.
- W4387448185 hasConceptScore W4387448185C154945302 @default.
- W4387448185 hasConceptScore W4387448185C177264268 @default.
- W4387448185 hasConceptScore W4387448185C18969341 @default.
- W4387448185 hasConceptScore W4387448185C199360897 @default.
- W4387448185 hasConceptScore W4387448185C207347870 @default.
- W4387448185 hasConceptScore W4387448185C2776401178 @default.
- W4387448185 hasConceptScore W4387448185C2776760102 @default.
- W4387448185 hasConceptScore W4387448185C2777212361 @default.
- W4387448185 hasConceptScore W4387448185C41008148 @default.
- W4387448185 hasConceptScore W4387448185C41895202 @default.
- W4387448185 hasConceptScore W4387448185C76155785 @default.
- W4387448185 hasConceptScore W4387448185C81917197 @default.
- W4387448185 hasConceptScore W4387448185C97541855 @default.
- W4387448185 hasConceptScore W4387448185C98045186 @default.
- W4387448185 hasLocation W43874481851 @default.
- W4387448185 hasOpenAccess W4387448185 @default.
- W4387448185 hasPrimaryLocation W43874481851 @default.
- W4387448185 hasRelatedWork W1974473538 @default.
- W4387448185 hasRelatedWork W1982853263 @default.
- W4387448185 hasRelatedWork W2020010749 @default.
- W4387448185 hasRelatedWork W2066003895 @default.
- W4387448185 hasRelatedWork W2120801881 @default.
- W4387448185 hasRelatedWork W2349788282 @default.
- W4387448185 hasRelatedWork W2537762514 @default.