Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210273945> ?p ?o ?g. }
- W4210273945 endingPage "444" @default.
- W4210273945 startingPage "435" @default.
- W4210273945 abstract "Human interaction recognition (HIR) is challenging due to multiple humans’ involvement and their mutual interaction in a single frame, generated from their movements. Mainstream literature is based on three-dimensional (3-D) convolutional neural networks (CNNs), processing only visual frames, where human joints data play a vital role in accurate interaction recognition. Therefore, this article proposes a multistream network for HIR that intelligently learns from skeletons’ key points and spatiotemporal visual representations. The first stream localises the joints of the human body using a pose estimation model and transmits them to a 1-D CNN and bidirectional long short-term memory to efficiently extract the features of the dynamic movements of each human skeleton. The second stream feeds the series of visual frames to a 3-D convolutional neural network to extract the discriminative spatiotemporal features. Finally, the outputs of both streams are integrated via fully connected layers that precisely classify the ongoing interactions between humans. To validate the performance of the proposed network, we conducted a comprehensive set of experiments on two benchmark datasets, UT-interaction and TV human interaction, and found 1.15% and 10.0% improvement in the accuracy." @default.
- W4210273945 created "2022-02-08" @default.
- W4210273945 creator A5028503461 @default.
- W4210273945 creator A5034370634 @default.
- W4210273945 creator A5034945583 @default.
- W4210273945 creator A5042536975 @default.
- W4210273945 creator A5044144622 @default.
- W4210273945 creator A5052654998 @default.
- W4210273945 creator A5072407810 @default.
- W4210273945 creator A5090689566 @default.
- W4210273945 date "2022-06-01" @default.
- W4210273945 modified "2023-10-04" @default.
- W4210273945 title "A Multi-Stream Sequence Learning Framework for Human Interaction Recognition" @default.
- W4210273945 cites W109378472 @default.
- W4210273945 cites W1936750108 @default.
- W4210273945 cites W1947481528 @default.
- W4210273945 cites W1967336115 @default.
- W4210273945 cites W1983705368 @default.
- W4210273945 cites W1996478295 @default.
- W4210273945 cites W1997691213 @default.
- W4210273945 cites W2022633861 @default.
- W4210273945 cites W2025508903 @default.
- W4210273945 cites W2073246097 @default.
- W4210273945 cites W2104007069 @default.
- W4210273945 cites W2147615062 @default.
- W4210273945 cites W2175012183 @default.
- W4210273945 cites W2183035153 @default.
- W4210273945 cites W2185953016 @default.
- W4210273945 cites W2307770531 @default.
- W4210273945 cites W2382036597 @default.
- W4210273945 cites W2510185399 @default.
- W4210273945 cites W2530143578 @default.
- W4210273945 cites W2533503513 @default.
- W4210273945 cites W2548211577 @default.
- W4210273945 cites W2554082199 @default.
- W4210273945 cites W2559085405 @default.
- W4210273945 cites W2606294640 @default.
- W4210273945 cites W2620105270 @default.
- W4210273945 cites W2788865504 @default.
- W4210273945 cites W2886810500 @default.
- W4210273945 cites W2962730651 @default.
- W4210273945 cites W2964087927 @default.
- W4210273945 cites W2974686944 @default.
- W4210273945 cites W2996611683 @default.
- W4210273945 cites W3013477486 @default.
- W4210273945 cites W3013682536 @default.
- W4210273945 cites W3016209583 @default.
- W4210273945 cites W3021907900 @default.
- W4210273945 cites W3036066034 @default.
- W4210273945 cites W3040752674 @default.
- W4210273945 cites W3087594579 @default.
- W4210273945 cites W3090348690 @default.
- W4210273945 cites W3096014500 @default.
- W4210273945 cites W3099128265 @default.
- W4210273945 cites W3099632052 @default.
- W4210273945 cites W7859433 @default.
- W4210273945 doi "https://doi.org/10.1109/thms.2021.3138708" @default.
- W4210273945 hasPublicationYear "2022" @default.
- W4210273945 type Work @default.
- W4210273945 citedByCount "5" @default.
- W4210273945 countsByYear W42102739452022 @default.
- W4210273945 countsByYear W42102739452023 @default.
- W4210273945 crossrefType "journal-article" @default.
- W4210273945 hasAuthorship W4210273945A5028503461 @default.
- W4210273945 hasAuthorship W4210273945A5034370634 @default.
- W4210273945 hasAuthorship W4210273945A5034945583 @default.
- W4210273945 hasAuthorship W4210273945A5042536975 @default.
- W4210273945 hasAuthorship W4210273945A5044144622 @default.
- W4210273945 hasAuthorship W4210273945A5052654998 @default.
- W4210273945 hasAuthorship W4210273945A5072407810 @default.
- W4210273945 hasAuthorship W4210273945A5090689566 @default.
- W4210273945 hasConcept C119857082 @default.
- W4210273945 hasConcept C126042441 @default.
- W4210273945 hasConcept C13280743 @default.
- W4210273945 hasConcept C153180895 @default.
- W4210273945 hasConcept C154945302 @default.
- W4210273945 hasConcept C177264268 @default.
- W4210273945 hasConcept C185798385 @default.
- W4210273945 hasConcept C199360897 @default.
- W4210273945 hasConcept C205649164 @default.
- W4210273945 hasConcept C41008148 @default.
- W4210273945 hasConcept C76155785 @default.
- W4210273945 hasConcept C81363708 @default.
- W4210273945 hasConcept C97931131 @default.
- W4210273945 hasConceptScore W4210273945C119857082 @default.
- W4210273945 hasConceptScore W4210273945C126042441 @default.
- W4210273945 hasConceptScore W4210273945C13280743 @default.
- W4210273945 hasConceptScore W4210273945C153180895 @default.
- W4210273945 hasConceptScore W4210273945C154945302 @default.
- W4210273945 hasConceptScore W4210273945C177264268 @default.
- W4210273945 hasConceptScore W4210273945C185798385 @default.
- W4210273945 hasConceptScore W4210273945C199360897 @default.
- W4210273945 hasConceptScore W4210273945C205649164 @default.
- W4210273945 hasConceptScore W4210273945C41008148 @default.
- W4210273945 hasConceptScore W4210273945C76155785 @default.
- W4210273945 hasConceptScore W4210273945C81363708 @default.
- W4210273945 hasConceptScore W4210273945C97931131 @default.
- W4210273945 hasFunder F4320322120 @default.