Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315643841> ?p ?o ?g. }
- W4315643841 endingPage "300" @default.
- W4315643841 startingPage "292" @default.
- W4315643841 abstract "In recent years, with the development of deep learning technology, computer vision and natural language processing have made significant progress, and establishing the relationship between computer vision and natural language processing has attracted more and more attention. The spatio-temporal images taken by satellites or aircrafts and scene images with people and other things are the main focus area. Existing methods have yielded excellent results in image–text matching, but there is still room for improvement in effectively using coarse and fine-grained information. We propose a method to solve this problem using multi-scale graph convolutional neural networks. We extracted the multi-scale features of images and texts for matching separately. Global and local matching are used to calculate the overall image sentence and local image–word similarity. Local matching is divided into two stages, first, the node level matches the correspondence between the learning region and the word. Next, the structure level matches the correspondence between the learning region and the phrase to make the matching more comprehensive. Finally, we verified our model on Flickr30k, MSCOCO and RSICD datasets." @default.
- W4315643841 created "2023-01-12" @default.
- W4315643841 creator A5012858566 @default.
- W4315643841 creator A5019281790 @default.
- W4315643841 creator A5020754606 @default.
- W4315643841 creator A5054991337 @default.
- W4315643841 creator A5077343840 @default.
- W4315643841 date "2023-05-01" @default.
- W4315643841 modified "2023-09-26" @default.
- W4315643841 title "Multi-scale image–text matching network for scene and spatio-temporal images" @default.
- W4315643841 cites W1905882502 @default.
- W4315643841 cites W1916445035 @default.
- W4315643841 cites W2034196113 @default.
- W4315643841 cites W2185175083 @default.
- W4315643841 cites W2552579943 @default.
- W4315643841 cites W2606473278 @default.
- W4315643841 cites W2745461083 @default.
- W4315643841 cites W2778100917 @default.
- W4315643841 cites W2962964995 @default.
- W4315643841 cites W2963040148 @default.
- W4315643841 cites W2963389687 @default.
- W4315643841 cites W2963467339 @default.
- W4315643841 cites W2964120214 @default.
- W4315643841 cites W2964727037 @default.
- W4315643841 cites W2988823324 @default.
- W4315643841 cites W2990571534 @default.
- W4315643841 cites W2994818707 @default.
- W4315643841 cites W2998215884 @default.
- W4315643841 cites W3010277541 @default.
- W4315643841 cites W3027386589 @default.
- W4315643841 cites W3035454331 @default.
- W4315643841 cites W3035552787 @default.
- W4315643841 cites W3035588244 @default.
- W4315643841 cites W3035605030 @default.
- W4315643841 cites W3100245404 @default.
- W4315643841 cites W3118694826 @default.
- W4315643841 cites W3138641322 @default.
- W4315643841 cites W3172793889 @default.
- W4315643841 cites W3213100861 @default.
- W4315643841 doi "https://doi.org/10.1016/j.future.2023.01.004" @default.
- W4315643841 hasPublicationYear "2023" @default.
- W4315643841 type Work @default.
- W4315643841 citedByCount "0" @default.
- W4315643841 crossrefType "journal-article" @default.
- W4315643841 hasAuthorship W4315643841A5012858566 @default.
- W4315643841 hasAuthorship W4315643841A5019281790 @default.
- W4315643841 hasAuthorship W4315643841A5020754606 @default.
- W4315643841 hasAuthorship W4315643841A5054991337 @default.
- W4315643841 hasAuthorship W4315643841A5077343840 @default.
- W4315643841 hasBestOaLocation W43156438411 @default.
- W4315643841 hasConcept C103278499 @default.
- W4315643841 hasConcept C105795698 @default.
- W4315643841 hasConcept C108583219 @default.
- W4315643841 hasConcept C115961682 @default.
- W4315643841 hasConcept C120665830 @default.
- W4315643841 hasConcept C121332964 @default.
- W4315643841 hasConcept C132525143 @default.
- W4315643841 hasConcept C138885662 @default.
- W4315643841 hasConcept C153180895 @default.
- W4315643841 hasConcept C154945302 @default.
- W4315643841 hasConcept C165064840 @default.
- W4315643841 hasConcept C192209626 @default.
- W4315643841 hasConcept C204321447 @default.
- W4315643841 hasConcept C2776224158 @default.
- W4315643841 hasConcept C2777530160 @default.
- W4315643841 hasConcept C2778755073 @default.
- W4315643841 hasConcept C31972630 @default.
- W4315643841 hasConcept C33923547 @default.
- W4315643841 hasConcept C41008148 @default.
- W4315643841 hasConcept C41895202 @default.
- W4315643841 hasConcept C62520636 @default.
- W4315643841 hasConcept C80444323 @default.
- W4315643841 hasConcept C81363708 @default.
- W4315643841 hasConcept C90805587 @default.
- W4315643841 hasConceptScore W4315643841C103278499 @default.
- W4315643841 hasConceptScore W4315643841C105795698 @default.
- W4315643841 hasConceptScore W4315643841C108583219 @default.
- W4315643841 hasConceptScore W4315643841C115961682 @default.
- W4315643841 hasConceptScore W4315643841C120665830 @default.
- W4315643841 hasConceptScore W4315643841C121332964 @default.
- W4315643841 hasConceptScore W4315643841C132525143 @default.
- W4315643841 hasConceptScore W4315643841C138885662 @default.
- W4315643841 hasConceptScore W4315643841C153180895 @default.
- W4315643841 hasConceptScore W4315643841C154945302 @default.
- W4315643841 hasConceptScore W4315643841C165064840 @default.
- W4315643841 hasConceptScore W4315643841C192209626 @default.
- W4315643841 hasConceptScore W4315643841C204321447 @default.
- W4315643841 hasConceptScore W4315643841C2776224158 @default.
- W4315643841 hasConceptScore W4315643841C2777530160 @default.
- W4315643841 hasConceptScore W4315643841C2778755073 @default.
- W4315643841 hasConceptScore W4315643841C31972630 @default.
- W4315643841 hasConceptScore W4315643841C33923547 @default.
- W4315643841 hasConceptScore W4315643841C41008148 @default.
- W4315643841 hasConceptScore W4315643841C41895202 @default.
- W4315643841 hasConceptScore W4315643841C62520636 @default.
- W4315643841 hasConceptScore W4315643841C80444323 @default.
- W4315643841 hasConceptScore W4315643841C81363708 @default.
- W4315643841 hasConceptScore W4315643841C90805587 @default.