Matches in SemOpenAlex for { <https://semopenalex.org/work/W4255957727> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4255957727 abstract "<div>Skeleton based human activity recognition has attracted lots of attention due to its wide range of applications. Skeleton data includes two or three dimensional coordinates of body joints. All of the body joints are not effective in recognizing different activities, so finding key joints within a video and across different activities has a significant role in improving the performance. In this paper we propose a novel framework that performs joint selection in skeleton video frames for the purpose of human activity recognition. To this end, we formulate the joint selection problem as a Markov Decision Process (MDP) where we employ deep reinforcement learning to find the most informative joints per frame. The proposed joint selection method is a general framework that can be employed to improve human activity classification methods. Experimental results on two benchmark activity recognition data sets using three different classifiers demonstrate effectiveness of the proposed joint selection method.</div>" @default.
- W4255957727 created "2022-05-12" @default.
- W4255957727 creator A5019976435 @default.
- W4255957727 creator A5073955046 @default.
- W4255957727 date "2021-07-07" @default.
- W4255957727 modified "2023-09-27" @default.
- W4255957727 title "Joint Selection using Deep Reinforcement Learning for Skeleton-based Activity Recognition" @default.
- W4255957727 doi "https://doi.org/10.36227/techrxiv.14887869" @default.
- W4255957727 hasPublicationYear "2021" @default.
- W4255957727 type Work @default.
- W4255957727 citedByCount "0" @default.
- W4255957727 crossrefType "posted-content" @default.
- W4255957727 hasAuthorship W4255957727A5019976435 @default.
- W4255957727 hasAuthorship W4255957727A5073955046 @default.
- W4255957727 hasBestOaLocation W42559577271 @default.
- W4255957727 hasConcept C119857082 @default.
- W4255957727 hasConcept C121687571 @default.
- W4255957727 hasConcept C126042441 @default.
- W4255957727 hasConcept C127413603 @default.
- W4255957727 hasConcept C13280743 @default.
- W4255957727 hasConcept C153180895 @default.
- W4255957727 hasConcept C154945302 @default.
- W4255957727 hasConcept C170154142 @default.
- W4255957727 hasConcept C18555067 @default.
- W4255957727 hasConcept C185798385 @default.
- W4255957727 hasConcept C18969341 @default.
- W4255957727 hasConcept C199360897 @default.
- W4255957727 hasConcept C205649164 @default.
- W4255957727 hasConcept C2777846634 @default.
- W4255957727 hasConcept C41008148 @default.
- W4255957727 hasConcept C76155785 @default.
- W4255957727 hasConcept C81917197 @default.
- W4255957727 hasConcept C97541855 @default.
- W4255957727 hasConceptScore W4255957727C119857082 @default.
- W4255957727 hasConceptScore W4255957727C121687571 @default.
- W4255957727 hasConceptScore W4255957727C126042441 @default.
- W4255957727 hasConceptScore W4255957727C127413603 @default.
- W4255957727 hasConceptScore W4255957727C13280743 @default.
- W4255957727 hasConceptScore W4255957727C153180895 @default.
- W4255957727 hasConceptScore W4255957727C154945302 @default.
- W4255957727 hasConceptScore W4255957727C170154142 @default.
- W4255957727 hasConceptScore W4255957727C18555067 @default.
- W4255957727 hasConceptScore W4255957727C185798385 @default.
- W4255957727 hasConceptScore W4255957727C18969341 @default.
- W4255957727 hasConceptScore W4255957727C199360897 @default.
- W4255957727 hasConceptScore W4255957727C205649164 @default.
- W4255957727 hasConceptScore W4255957727C2777846634 @default.
- W4255957727 hasConceptScore W4255957727C41008148 @default.
- W4255957727 hasConceptScore W4255957727C76155785 @default.
- W4255957727 hasConceptScore W4255957727C81917197 @default.
- W4255957727 hasConceptScore W4255957727C97541855 @default.
- W4255957727 hasLocation W42559577271 @default.
- W4255957727 hasLocation W42559577272 @default.
- W4255957727 hasOpenAccess W4255957727 @default.
- W4255957727 hasPrimaryLocation W42559577271 @default.
- W4255957727 hasRelatedWork W2144724818 @default.
- W4255957727 hasRelatedWork W2909020086 @default.
- W4255957727 hasRelatedWork W2946101226 @default.
- W4255957727 hasRelatedWork W2990973236 @default.
- W4255957727 hasRelatedWork W3011192796 @default.
- W4255957727 hasRelatedWork W3186553538 @default.
- W4255957727 hasRelatedWork W3214730717 @default.
- W4255957727 hasRelatedWork W4255957727 @default.
- W4255957727 hasRelatedWork W4315562691 @default.
- W4255957727 hasRelatedWork W4367844760 @default.
- W4255957727 isParatext "false" @default.
- W4255957727 isRetracted "false" @default.
- W4255957727 workType "article" @default.