Matches in SemOpenAlex for { <https://semopenalex.org/work/W3134738404> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3134738404 endingPage "12" @default.
- W3134738404 startingPage "1" @default.
- W3134738404 abstract "Compared with natural images, aerial images collected by satellite sensors/aerial cameras can provide a much larger field of view and often contain multiple objects of interest (multiple labels). There are certain limitations of existing multilabel aerial image classification methods. First, label correlations were often ignored in previous MAIC work, and thus, multilabel classifiers failed to be self-adapted. Second, existing multilabeled data sets for aerial images only cover limited images with fixed labels. Therefore, the underlying semantic correlations of labels cannot be fully included, while such correlation information is implicitly used as common knowledge by human beings. To tackle these concerns, we propose a novel multilabel classification method for aerial images. Our contributions are twofold. First, as the first attempt, label correlations are inferred from both the specific data set and ConceptNet (a popular knowledge graph for common sense). Second, based on graph neural network (GNN), we propose a novel end-to-end aerial image classification model, named the multiple label concept graph (ML-CG). ML-CG builds a concept graph to describe the semantic correlations from both the label set and the ConceptNet. We also incorporate both semantic attention and label attention in the GNN to better extract meaningful information of image labels. Compared with state-of-the-art methods, the effectiveness of the proposed method is demonstrated on both the commonly used UCM data set and a recently proposed DFC15 data set with high image resolution." @default.
- W3134738404 created "2021-03-15" @default.
- W3134738404 creator A5036724788 @default.
- W3134738404 creator A5046311124 @default.
- W3134738404 creator A5051587486 @default.
- W3134738404 creator A5053156190 @default.
- W3134738404 creator A5064078067 @default.
- W3134738404 date "2022-01-01" @default.
- W3134738404 modified "2023-10-17" @default.
- W3134738404 title "Multilabel Aerial Image Classification With a Concept Attention Graph Neural Network" @default.
- W3134738404 cites W2069525662 @default.
- W3134738404 cites W2114315281 @default.
- W3134738404 cites W2179290474 @default.
- W3134738404 cites W2194775991 @default.
- W3134738404 cites W2250539671 @default.
- W3134738404 cites W2343436245 @default.
- W3134738404 cites W2575479478 @default.
- W3134738404 cites W2579933644 @default.
- W3134738404 cites W2602837914 @default.
- W3134738404 cites W2766938848 @default.
- W3134738404 cites W2781911289 @default.
- W3134738404 cites W2790255518 @default.
- W3134738404 cites W2794176907 @default.
- W3134738404 cites W2795476700 @default.
- W3134738404 cites W2804982862 @default.
- W3134738404 cites W2884821995 @default.
- W3134738404 cites W2901576309 @default.
- W3134738404 cites W2932399282 @default.
- W3134738404 cites W2937749267 @default.
- W3134738404 cites W2946373483 @default.
- W3134738404 cites W2947443368 @default.
- W3134738404 cites W2963995737 @default.
- W3134738404 cites W2969974902 @default.
- W3134738404 cites W2626236803 @default.
- W3134738404 doi "https://doi.org/10.1109/tgrs.2020.3041461" @default.
- W3134738404 hasPublicationYear "2022" @default.
- W3134738404 type Work @default.
- W3134738404 sameAs 3134738404 @default.
- W3134738404 citedByCount "6" @default.
- W3134738404 countsByYear W31347384042021 @default.
- W3134738404 countsByYear W31347384042022 @default.
- W3134738404 countsByYear W31347384042023 @default.
- W3134738404 crossrefType "journal-article" @default.
- W3134738404 hasAuthorship W3134738404A5036724788 @default.
- W3134738404 hasAuthorship W3134738404A5046311124 @default.
- W3134738404 hasAuthorship W3134738404A5051587486 @default.
- W3134738404 hasAuthorship W3134738404A5053156190 @default.
- W3134738404 hasAuthorship W3134738404A5064078067 @default.
- W3134738404 hasConcept C115961682 @default.
- W3134738404 hasConcept C132525143 @default.
- W3134738404 hasConcept C153180895 @default.
- W3134738404 hasConcept C154945302 @default.
- W3134738404 hasConcept C177264268 @default.
- W3134738404 hasConcept C199360897 @default.
- W3134738404 hasConcept C2776429412 @default.
- W3134738404 hasConcept C41008148 @default.
- W3134738404 hasConcept C50644808 @default.
- W3134738404 hasConcept C51632099 @default.
- W3134738404 hasConcept C58489278 @default.
- W3134738404 hasConcept C75294576 @default.
- W3134738404 hasConcept C80444323 @default.
- W3134738404 hasConceptScore W3134738404C115961682 @default.
- W3134738404 hasConceptScore W3134738404C132525143 @default.
- W3134738404 hasConceptScore W3134738404C153180895 @default.
- W3134738404 hasConceptScore W3134738404C154945302 @default.
- W3134738404 hasConceptScore W3134738404C177264268 @default.
- W3134738404 hasConceptScore W3134738404C199360897 @default.
- W3134738404 hasConceptScore W3134738404C2776429412 @default.
- W3134738404 hasConceptScore W3134738404C41008148 @default.
- W3134738404 hasConceptScore W3134738404C50644808 @default.
- W3134738404 hasConceptScore W3134738404C51632099 @default.
- W3134738404 hasConceptScore W3134738404C58489278 @default.
- W3134738404 hasConceptScore W3134738404C75294576 @default.
- W3134738404 hasConceptScore W3134738404C80444323 @default.
- W3134738404 hasFunder F4320321001 @default.
- W3134738404 hasFunder F4320322725 @default.
- W3134738404 hasFunder F4320335787 @default.
- W3134738404 hasLocation W31347384041 @default.
- W3134738404 hasOpenAccess W3134738404 @default.
- W3134738404 hasPrimaryLocation W31347384041 @default.
- W3134738404 hasRelatedWork W133358225 @default.
- W3134738404 hasRelatedWork W1577137544 @default.
- W3134738404 hasRelatedWork W2041525275 @default.
- W3134738404 hasRelatedWork W2508908072 @default.
- W3134738404 hasRelatedWork W2509146328 @default.
- W3134738404 hasRelatedWork W2537156416 @default.
- W3134738404 hasRelatedWork W2742991909 @default.
- W3134738404 hasRelatedWork W2996038082 @default.
- W3134738404 hasRelatedWork W4323767780 @default.
- W3134738404 hasRelatedWork W7626849 @default.
- W3134738404 hasVolume "60" @default.
- W3134738404 isParatext "false" @default.
- W3134738404 isRetracted "false" @default.
- W3134738404 magId "3134738404" @default.
- W3134738404 workType "article" @default.