Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309047078> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4309047078 endingPage "601" @default.
- W4309047078 startingPage "593" @default.
- W4309047078 abstract "Image-text matching aims to make a connection between visual and natural information. Some of the current methods have made great progress by using global alignment between images and sentences and local alignment between the image region and its corresponding word. However, the importance of the correlation between global alignment and local alignment is ignored to some extends. Therefore, in this paper, we propose a new region feature enhancement-based image text similarity inference network. Firstly, the image region feature is enhanced by graph convolutional neural network, which is used to find the correlation among different image region features with the production of features’ sematic relationship. Secondly, we propose a vector-based similarity representation to describe local and global alignment with a more comprehensive way. Finally, a graph convolution neural network is introduced to construct a similarity graph for propagating correlation between local alignment and global alignment to every part. By testing on the MSCOCO and Flickr30k dataset, our proposed method shows great accuracy performance and competitiveness." @default.
- W4309047078 created "2022-11-21" @default.
- W4309047078 creator A5028567439 @default.
- W4309047078 creator A5059811201 @default.
- W4309047078 creator A5061933200 @default.
- W4309047078 creator A5072942701 @default.
- W4309047078 creator A5084925986 @default.
- W4309047078 date "2023-01-01" @default.
- W4309047078 modified "2023-09-26" @default.
- W4309047078 title "RFE-SRN: Image-text similarity reasoning network based on regional feature enhancement" @default.
- W4309047078 cites W2277195237 @default.
- W4309047078 cites W2481240925 @default.
- W4309047078 cites W2606473278 @default.
- W4309047078 cites W2962964995 @default.
- W4309047078 cites W2964216321 @default.
- W4309047078 cites W3029678209 @default.
- W4309047078 cites W3035454331 @default.
- W4309047078 cites W3172884193 @default.
- W4309047078 cites W639708223 @default.
- W4309047078 doi "https://doi.org/10.1016/j.neucom.2022.11.003" @default.
- W4309047078 hasPublicationYear "2023" @default.
- W4309047078 type Work @default.
- W4309047078 citedByCount "0" @default.
- W4309047078 crossrefType "journal-article" @default.
- W4309047078 hasAuthorship W4309047078A5028567439 @default.
- W4309047078 hasAuthorship W4309047078A5059811201 @default.
- W4309047078 hasAuthorship W4309047078A5061933200 @default.
- W4309047078 hasAuthorship W4309047078A5072942701 @default.
- W4309047078 hasAuthorship W4309047078A5084925986 @default.
- W4309047078 hasConcept C103278499 @default.
- W4309047078 hasConcept C105795698 @default.
- W4309047078 hasConcept C115961682 @default.
- W4309047078 hasConcept C132525143 @default.
- W4309047078 hasConcept C138885662 @default.
- W4309047078 hasConcept C153180895 @default.
- W4309047078 hasConcept C154945302 @default.
- W4309047078 hasConcept C165064840 @default.
- W4309047078 hasConcept C2776214188 @default.
- W4309047078 hasConcept C2776401178 @default.
- W4309047078 hasConcept C33923547 @default.
- W4309047078 hasConcept C41008148 @default.
- W4309047078 hasConcept C41895202 @default.
- W4309047078 hasConcept C80444323 @default.
- W4309047078 hasConcept C81363708 @default.
- W4309047078 hasConceptScore W4309047078C103278499 @default.
- W4309047078 hasConceptScore W4309047078C105795698 @default.
- W4309047078 hasConceptScore W4309047078C115961682 @default.
- W4309047078 hasConceptScore W4309047078C132525143 @default.
- W4309047078 hasConceptScore W4309047078C138885662 @default.
- W4309047078 hasConceptScore W4309047078C153180895 @default.
- W4309047078 hasConceptScore W4309047078C154945302 @default.
- W4309047078 hasConceptScore W4309047078C165064840 @default.
- W4309047078 hasConceptScore W4309047078C2776214188 @default.
- W4309047078 hasConceptScore W4309047078C2776401178 @default.
- W4309047078 hasConceptScore W4309047078C33923547 @default.
- W4309047078 hasConceptScore W4309047078C41008148 @default.
- W4309047078 hasConceptScore W4309047078C41895202 @default.
- W4309047078 hasConceptScore W4309047078C80444323 @default.
- W4309047078 hasConceptScore W4309047078C81363708 @default.
- W4309047078 hasLocation W43090470781 @default.
- W4309047078 hasOpenAccess W4309047078 @default.
- W4309047078 hasPrimaryLocation W43090470781 @default.
- W4309047078 hasRelatedWork W2295021132 @default.
- W4309047078 hasRelatedWork W2546942002 @default.
- W4309047078 hasRelatedWork W2767651786 @default.
- W4309047078 hasRelatedWork W2786306966 @default.
- W4309047078 hasRelatedWork W2886673456 @default.
- W4309047078 hasRelatedWork W2912288872 @default.
- W4309047078 hasRelatedWork W2970216048 @default.
- W4309047078 hasRelatedWork W3106036237 @default.
- W4309047078 hasRelatedWork W564581980 @default.
- W4309047078 hasRelatedWork W785854688 @default.
- W4309047078 hasVolume "518" @default.
- W4309047078 isParatext "false" @default.
- W4309047078 isRetracted "false" @default.
- W4309047078 workType "article" @default.