Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206111836> ?p ?o ?g. }
- W4206111836 endingPage "16" @default.
- W4206111836 startingPage "1" @default.
- W4206111836 abstract "The encoder–decoder framework is prevalent in existing remote-sensing image captioning (RSIC) models. The appearance of attention mechanisms brings significant results. However, current attention-based caption models only build up the relationships between the local features without introducing the global visual feature and removing redundant feature components. It will cause caption models to generate descriptive sentences that are weakly related to the scene of images. To solve the problems, this article proposed a global visual feature-guided attention (GVFGA) mechanism. First, GVFGA introduces the global visual feature and fuses them with local visual features to build up their relationships between them. Second, an attention gate utilizing the global visual feature is proposed in GVFGA to filter out redundant feature components in the fused image features and provide more salient image features. In addition, to relieve the hidden state’s burden, a linguistic state (LS) is proposed to specifically provide textual features, making the hidden state only guiding visual–textual attention process. What’s more, to further refine the fusion of visual features and textual features, a LS-Guided Attention (LSGA) mechanism is proposed. It can also filter out the irrelevant information in the fused visual–textual feature with the help of an attention gate. The experimental results show that this proposed image captioning model can achieve better results on three RSIC datasets, UCM-Captions, Sydney-Captions, and RSICD datasets." @default.
- W4206111836 created "2022-01-25" @default.
- W4206111836 creator A5002059265 @default.
- W4206111836 creator A5005905514 @default.
- W4206111836 creator A5052182167 @default.
- W4206111836 creator A5056275120 @default.
- W4206111836 creator A5059827848 @default.
- W4206111836 creator A5074960174 @default.
- W4206111836 date "2022-01-01" @default.
- W4206111836 modified "2023-10-17" @default.
- W4206111836 title "Global Visual Feature and Linguistic State Guided Attention for Remote Sensing Image Captioning" @default.
- W4206111836 cites W1536680647 @default.
- W4206111836 cites W1895577753 @default.
- W4206111836 cites W1903029394 @default.
- W4206111836 cites W1956340063 @default.
- W4206111836 cites W1980038761 @default.
- W4206111836 cites W2064675550 @default.
- W4206111836 cites W2086866337 @default.
- W4206111836 cites W2101105183 @default.
- W4206111836 cites W2102605133 @default.
- W4206111836 cites W2108598243 @default.
- W4206111836 cites W2117539524 @default.
- W4206111836 cites W2133459682 @default.
- W4206111836 cites W2133512280 @default.
- W4206111836 cites W2194775991 @default.
- W4206111836 cites W2412782625 @default.
- W4206111836 cites W2603566245 @default.
- W4206111836 cites W2607768201 @default.
- W4206111836 cites W2618530766 @default.
- W4206111836 cites W2745461083 @default.
- W4206111836 cites W2774965253 @default.
- W4206111836 cites W2807834696 @default.
- W4206111836 cites W2829067510 @default.
- W4206111836 cites W2911584214 @default.
- W4206111836 cites W2920981979 @default.
- W4206111836 cites W2945223572 @default.
- W4206111836 cites W2963175879 @default.
- W4206111836 cites W2973586224 @default.
- W4206111836 cites W2979924880 @default.
- W4206111836 cites W2986670728 @default.
- W4206111836 cites W2995904231 @default.
- W4206111836 cites W3006487741 @default.
- W4206111836 cites W3015625772 @default.
- W4206111836 cites W3026441479 @default.
- W4206111836 cites W3030602447 @default.
- W4206111836 cites W3037422790 @default.
- W4206111836 cites W3046260628 @default.
- W4206111836 cites W3089915566 @default.
- W4206111836 cites W3093088671 @default.
- W4206111836 cites W3095909497 @default.
- W4206111836 cites W3100245404 @default.
- W4206111836 cites W3157519352 @default.
- W4206111836 cites W3183824823 @default.
- W4206111836 cites W639708223 @default.
- W4206111836 doi "https://doi.org/10.1109/tgrs.2021.3132095" @default.
- W4206111836 hasPublicationYear "2022" @default.
- W4206111836 type Work @default.
- W4206111836 citedByCount "8" @default.
- W4206111836 countsByYear W42061118362022 @default.
- W4206111836 countsByYear W42061118362023 @default.
- W4206111836 crossrefType "journal-article" @default.
- W4206111836 hasAuthorship W4206111836A5002059265 @default.
- W4206111836 hasAuthorship W4206111836A5005905514 @default.
- W4206111836 hasAuthorship W4206111836A5052182167 @default.
- W4206111836 hasAuthorship W4206111836A5056275120 @default.
- W4206111836 hasAuthorship W4206111836A5059827848 @default.
- W4206111836 hasAuthorship W4206111836A5074960174 @default.
- W4206111836 hasConcept C106131492 @default.
- W4206111836 hasConcept C111919701 @default.
- W4206111836 hasConcept C115961682 @default.
- W4206111836 hasConcept C118505674 @default.
- W4206111836 hasConcept C138885662 @default.
- W4206111836 hasConcept C153180895 @default.
- W4206111836 hasConcept C154945302 @default.
- W4206111836 hasConcept C157657479 @default.
- W4206111836 hasConcept C2776401178 @default.
- W4206111836 hasConcept C2780719617 @default.
- W4206111836 hasConcept C31972630 @default.
- W4206111836 hasConcept C36464697 @default.
- W4206111836 hasConcept C41008148 @default.
- W4206111836 hasConcept C41895202 @default.
- W4206111836 hasConcept C98045186 @default.
- W4206111836 hasConceptScore W4206111836C106131492 @default.
- W4206111836 hasConceptScore W4206111836C111919701 @default.
- W4206111836 hasConceptScore W4206111836C115961682 @default.
- W4206111836 hasConceptScore W4206111836C118505674 @default.
- W4206111836 hasConceptScore W4206111836C138885662 @default.
- W4206111836 hasConceptScore W4206111836C153180895 @default.
- W4206111836 hasConceptScore W4206111836C154945302 @default.
- W4206111836 hasConceptScore W4206111836C157657479 @default.
- W4206111836 hasConceptScore W4206111836C2776401178 @default.
- W4206111836 hasConceptScore W4206111836C2780719617 @default.
- W4206111836 hasConceptScore W4206111836C31972630 @default.
- W4206111836 hasConceptScore W4206111836C36464697 @default.
- W4206111836 hasConceptScore W4206111836C41008148 @default.
- W4206111836 hasConceptScore W4206111836C41895202 @default.
- W4206111836 hasConceptScore W4206111836C98045186 @default.
- W4206111836 hasFunder F4320334953 @default.