FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387046305> ?p ?o ?g. }

• W4387046305 endingPage "121789" @default.
• W4387046305 startingPage "121789" @default.
• W4387046305 abstract "Multisensor image fusion is a challenging task that aims to produce a composite image by fusing visible (VI) and infrared (IR) images. Deep neural networks have shown impressive performance for VI and IR image fusion however, majority of them overlook the internal patch-recurrence property of source images, which limits their ability to learn diverse features. To address this issue, we propose a novel fusion framework based on vision transformer and graph attention, utilizing local patch repetition to enhance the feature representation and texture recovery. In particular, the proposed transformer blocks can learn high-frequency domain-specific information of the source images. The graph attention mechanism provides additional guidance for the features utilizing the similarity and symmetry information across patches. Furthermore, the proposed graph attention fusion block (GAFB) improves the selectivity and effectiveness of feature learning. The GAFB can identify significant corresponding local and global details of source images. The complementary information containing long-range and local symmetric details across domains is combined while preserving the appropriate apparent intensity to generate the fused image. Through extensive evaluations on benchmark datasets, our proposed technique demonstrates superior performance. Significantly, our approach achieves SSIM scores of 0.7552 on the TNO dataset and 0.7673 on the roadscene dataset, surpassing the state-of-the-art techniques used for evaluation." @default.
• W4387046305 created "2023-09-27" @default.
• W4387046305 creator A5079232252 @default.
• W4387046305 creator A5085156714 @default.
• W4387046305 creator A5086648739 @default.
• W4387046305 date "2023-09-01" @default.
• W4387046305 modified "2023-10-06" @default.
• W4387046305 title "TGF: Multiscale transformer graph attention network for multi-sensor image fusion" @default.
• W4387046305 cites W2004913087 @default.
• W4387046305 cites W2020442368 @default.
• W4387046305 cites W2026651590 @default.
• W4387046305 cites W2082232962 @default.
• W4387046305 cites W2115214993 @default.
• W4387046305 cites W2133665775 @default.
• W4387046305 cites W2153868441 @default.
• W4387046305 cites W2154053567 @default.
• W4387046305 cites W2266694576 @default.
• W4387046305 cites W2767658511 @default.
• W4387046305 cites W2772136803 @default.
• W4387046305 cites W2912147220 @default.
• W4387046305 cites W2950648852 @default.
• W4387046305 cites W2963037989 @default.
• W4387046305 cites W2963530785 @default.
• W4387046305 cites W2963787388 @default.
• W4387046305 cites W2999838674 @default.
• W4387046305 cites W3030921250 @default.
• W4387046305 cites W3034971973 @default.
• W4387046305 cites W3035571898 @default.
• W4387046305 cites W3036032447 @default.
• W4387046305 cites W3102411220 @default.
• W4387046305 cites W3105639468 @default.
• W4387046305 cites W3107998196 @default.
• W4387046305 cites W3113560462 @default.
• W4387046305 cites W3121751387 @default.
• W4387046305 cites W3126855404 @default.
• W4387046305 cites W3158383274 @default.
• W4387046305 cites W3213384164 @default.
• W4387046305 cites W4210385745 @default.
• W4387046305 cites W4214709091 @default.
• W4387046305 cites W4214947578 @default.
• W4387046305 cites W4221052885 @default.
• W4387046305 cites W4221053356 @default.
• W4387046305 cites W4226178544 @default.
• W4387046305 cites W4283732315 @default.
• W4387046305 cites W4286361941 @default.
• W4387046305 cites W4288069902 @default.
• W4387046305 cites W4293386311 @default.
• W4387046305 cites W4297833146 @default.
• W4387046305 cites W4312594135 @default.
• W4387046305 cites W4386179772 @default.
• W4387046305 doi "https://doi.org/10.1016/j.eswa.2023.121789" @default.
• W4387046305 hasPublicationYear "2023" @default.
• W4387046305 type Work @default.
• W4387046305 citedByCount "0" @default.
• W4387046305 crossrefType "journal-article" @default.
• W4387046305 hasAuthorship W4387046305A5079232252 @default.
• W4387046305 hasAuthorship W4387046305A5085156714 @default.
• W4387046305 hasAuthorship W4387046305A5086648739 @default.
• W4387046305 hasConcept C121332964 @default.
• W4387046305 hasConcept C132525143 @default.
• W4387046305 hasConcept C13280743 @default.
• W4387046305 hasConcept C153180895 @default.
• W4387046305 hasConcept C154945302 @default.
• W4387046305 hasConcept C165801399 @default.
• W4387046305 hasConcept C185798385 @default.
• W4387046305 hasConcept C205649164 @default.
• W4387046305 hasConcept C41008148 @default.
• W4387046305 hasConcept C62520636 @default.
• W4387046305 hasConcept C66322947 @default.
• W4387046305 hasConcept C80444323 @default.
• W4387046305 hasConceptScore W4387046305C121332964 @default.
• W4387046305 hasConceptScore W4387046305C132525143 @default.
• W4387046305 hasConceptScore W4387046305C13280743 @default.
• W4387046305 hasConceptScore W4387046305C153180895 @default.
• W4387046305 hasConceptScore W4387046305C154945302 @default.
• W4387046305 hasConceptScore W4387046305C165801399 @default.
• W4387046305 hasConceptScore W4387046305C185798385 @default.
• W4387046305 hasConceptScore W4387046305C205649164 @default.
• W4387046305 hasConceptScore W4387046305C41008148 @default.
• W4387046305 hasConceptScore W4387046305C62520636 @default.
• W4387046305 hasConceptScore W4387046305C66322947 @default.
• W4387046305 hasConceptScore W4387046305C80444323 @default.
• W4387046305 hasFunder F4320321408 @default.
• W4387046305 hasFunder F4320322120 @default.
• W4387046305 hasLocation W43870463051 @default.
• W4387046305 hasOpenAccess W4387046305 @default.
• W4387046305 hasPrimaryLocation W43870463051 @default.
• W4387046305 hasRelatedWork W2028665553 @default.
• W4387046305 hasRelatedWork W2033914206 @default.
• W4387046305 hasRelatedWork W2042327336 @default.
• W4387046305 hasRelatedWork W2086519370 @default.
• W4387046305 hasRelatedWork W2087343574 @default.
• W4387046305 hasRelatedWork W2130974462 @default.
• W4387046305 hasRelatedWork W2378211422 @default.
• W4387046305 hasRelatedWork W2535915176 @default.
• W4387046305 hasRelatedWork W4321353415 @default.
• W4387046305 hasRelatedWork W972276598 @default.
• W4387046305 isParatext "false" @default.

• next