FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221060219> ?p ?o ?g. }

• W4221060219 endingPage "231" @default.
• W4221060219 startingPage "217" @default.
• W4221060219 abstract "Video-based group activities typically contain interactive contexts among diverse visual modalities between multiple persons, and semantic relationships between individual actions. Nevertheless, majority of the existing methods for recognizing group activity either captures the relationships among different persons by utilizing a solely RGB modality or neglect to exploit the label hierarchies between individual actions and the group activity. To tackle these issues, we propose a visual-semantic graph neural network, with pose-position attentive learning (VSGNN-PAL), for group activity recognition. Specifically, we first extract the individual-level appearance and motion representations from RGB and optical-flow inputs, to build a bi-modal visual graph. Two attentive aggregators are further proposed to integrate both the pose and position information to measure the relevance scores between persons, and dynamically refine the representation of each visual node from both modality-specific and cross-modal perspectives. To model a semantic hierarchy from a label space, we construct a semantic graph based on the linguistic embeddings of individual actions and group activity labels. We further employ a bi-directional mapping learning scheme, to integrate the label-relation-aware semantic context into the visual representations. Besides, a global reasoning module is introduced to progressively generate the group-level representations with the scene description maintained. Furthermore, we formulate a semantic-preserving loss, to maintain the consistency between the learned high-level representations and the semantics of the ground-truth labels. Experimental results on three group activity benchmarks demonstrate that the proposed method achieves state-of-the-art performance." @default.
• W4221060219 created "2022-04-03" @default.
• W4221060219 creator A5005068793 @default.
• W4221060219 creator A5011105024 @default.
• W4221060219 creator A5019678322 @default.
• W4221060219 creator A5090581248 @default.
• W4221060219 date "2022-06-01" @default.
• W4221060219 modified "2023-10-18" @default.
• W4221060219 title "Visual-semantic graph neural network with pose-position attentive learning for group activity recognition" @default.
• W4221060219 cites W100367037 @default.
• W4221060219 cites W1861492603 @default.
• W4221060219 cites W2053619738 @default.
• W4221060219 cites W2259801182 @default.
• W4221060219 cites W2269938945 @default.
• W4221060219 cites W2558630670 @default.
• W4221060219 cites W2736442062 @default.
• W4221060219 cites W2778252923 @default.
• W4221060219 cites W2798429327 @default.
• W4221060219 cites W2888096830 @default.
• W4221060219 cites W289401892 @default.
• W4221060219 cites W2895064504 @default.
• W4221060219 cites W2914868535 @default.
• W4221060219 cites W2916798096 @default.
• W4221060219 cites W2927778007 @default.
• W4221060219 cites W2932399282 @default.
• W4221060219 cites W2940963663 @default.
• W4221060219 cites W2947315758 @default.
• W4221060219 cites W2963076818 @default.
• W4221060219 cites W2963091558 @default.
• W4221060219 cites W2963150697 @default.
• W4221060219 cites W2963377215 @default.
• W4221060219 cites W2963524571 @default.
• W4221060219 cites W2963907063 @default.
• W4221060219 cites W2998420437 @default.
• W4221060219 cites W3009811369 @default.
• W4221060219 cites W3033116542 @default.
• W4221060219 cites W3035029089 @default.
• W4221060219 cites W3048602385 @default.
• W4221060219 cites W3095013945 @default.
• W4221060219 cites W3096719817 @default.
• W4221060219 cites W3105000568 @default.
• W4221060219 cites W3107320732 @default.
• W4221060219 cites W3110257409 @default.
• W4221060219 cites W3157033490 @default.
• W4221060219 cites W3200370223 @default.
• W4221060219 cites W3217059328 @default.
• W4221060219 cites W4205432963 @default.
• W4221060219 cites W4230451144 @default.
• W4221060219 cites W639708223 @default.
• W4221060219 doi "https://doi.org/10.1016/j.neucom.2022.03.066" @default.
• W4221060219 hasPublicationYear "2022" @default.
• W4221060219 type Work @default.
• W4221060219 citedByCount "9" @default.
• W4221060219 countsByYear W42210602192022 @default.
• W4221060219 countsByYear W42210602192023 @default.
• W4221060219 crossrefType "journal-article" @default.
• W4221060219 hasAuthorship W4221060219A5005068793 @default.
• W4221060219 hasAuthorship W4221060219A5011105024 @default.
• W4221060219 hasAuthorship W4221060219A5019678322 @default.
• W4221060219 hasAuthorship W4221060219A5090581248 @default.
• W4221060219 hasConcept C119857082 @default.
• W4221060219 hasConcept C132525143 @default.
• W4221060219 hasConcept C153180895 @default.
• W4221060219 hasConcept C154945302 @default.
• W4221060219 hasConcept C204321447 @default.
• W4221060219 hasConcept C41008148 @default.
• W4221060219 hasConcept C80444323 @default.
• W4221060219 hasConceptScore W4221060219C119857082 @default.
• W4221060219 hasConceptScore W4221060219C132525143 @default.
• W4221060219 hasConceptScore W4221060219C153180895 @default.
• W4221060219 hasConceptScore W4221060219C154945302 @default.
• W4221060219 hasConceptScore W4221060219C204321447 @default.
• W4221060219 hasConceptScore W4221060219C41008148 @default.
• W4221060219 hasConceptScore W4221060219C80444323 @default.
• W4221060219 hasLocation W42210602191 @default.
• W4221060219 hasOpenAccess W4221060219 @default.
• W4221060219 hasPrimaryLocation W42210602191 @default.
• W4221060219 hasRelatedWork W2789919619 @default.
• W4221060219 hasRelatedWork W2961085424 @default.
• W4221060219 hasRelatedWork W3046775127 @default.
• W4221060219 hasRelatedWork W3170094116 @default.
• W4221060219 hasRelatedWork W4205958290 @default.
• W4221060219 hasRelatedWork W4285260836 @default.
• W4221060219 hasRelatedWork W4286629047 @default.
• W4221060219 hasRelatedWork W4306321456 @default.
• W4221060219 hasRelatedWork W4306674287 @default.
• W4221060219 hasRelatedWork W4224009465 @default.
• W4221060219 hasVolume "491" @default.
• W4221060219 isParatext "false" @default.
• W4221060219 isRetracted "false" @default.
• W4221060219 workType "article" @default.