Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385781682> ?p ?o ?g. }
- W4385781682 endingPage "171251" @default.
- W4385781682 startingPage "171251" @default.
- W4385781682 abstract "Infrared image contains typical targets characterized by pixel intensity distribution, while visible image preserves structural details represented by edges and gradient. Infrared and visible image fusion aims to merge their respective key information, and produce a more comprehensive image with superior target perception and better detail representation. Most existing methods cannot reach this goal well, and are easy to generate a limited fused result. Towards this end, a dual-path residual attention fusion network, namely DRAFusion, is proposed in this paper. We construct a multi-scale dense network architecture, which adequately aggregates horizontal and vertical intermediate features at all scales and layers. In the fusion layer, we develop a residual attention fusion module, cascading channel-wise and spatial-wise attention models, which is used to model the global contextual dependencies, and interact with feature maps to more focus on their respective key information. In addition, we design a novel feature adaptation loss function to control the proportion of their key information in the training phase, which can keep a better balance between fused results and source images. Extensive experiments demonstrate that our DRAFusion produces a remarkable performance on the three testing datasets, and is superior to other methods in terms of qualitative visual description and quantitative evaluation validation." @default.
- W4385781682 created "2023-08-13" @default.
- W4385781682 creator A5056425792 @default.
- W4385781682 creator A5060099050 @default.
- W4385781682 creator A5068675549 @default.
- W4385781682 creator A5070412652 @default.
- W4385781682 creator A5086585682 @default.
- W4385781682 creator A5089572482 @default.
- W4385781682 date "2023-10-01" @default.
- W4385781682 modified "2023-10-17" @default.
- W4385781682 title "A dual-path residual attention fusion network for infrared and visible images" @default.
- W4385781682 cites W1580436348 @default.
- W4385781682 cites W1708141795 @default.
- W4385781682 cites W1756233291 @default.
- W4385781682 cites W2054273865 @default.
- W4385781682 cites W2770038176 @default.
- W4385781682 cites W2912147220 @default.
- W4385781682 cites W2963420686 @default.
- W4385781682 cites W2963787388 @default.
- W4385781682 cites W2981828152 @default.
- W4385781682 cites W2989707943 @default.
- W4385781682 cites W2999838674 @default.
- W4385781682 cites W3007891240 @default.
- W4385781682 cites W3011768656 @default.
- W4385781682 cites W3023203534 @default.
- W4385781682 cites W3102411220 @default.
- W4385781682 cites W3105639468 @default.
- W4385781682 cites W3107998196 @default.
- W4385781682 cites W3110670586 @default.
- W4385781682 cites W3126855404 @default.
- W4385781682 cites W3133700567 @default.
- W4385781682 cites W3143068962 @default.
- W4385781682 cites W3151960747 @default.
- W4385781682 cites W3185043317 @default.
- W4385781682 cites W3194077607 @default.
- W4385781682 cites W3198582484 @default.
- W4385781682 cites W3206506760 @default.
- W4385781682 cites W4206713196 @default.
- W4385781682 cites W4220893768 @default.
- W4385781682 cites W4225303376 @default.
- W4385781682 cites W4225852025 @default.
- W4385781682 cites W4226178544 @default.
- W4385781682 cites W4286361941 @default.
- W4385781682 cites W4312594135 @default.
- W4385781682 cites W4312737473 @default.
- W4385781682 cites W4312817981 @default.
- W4385781682 cites W4313555022 @default.
- W4385781682 cites W4317987737 @default.
- W4385781682 cites W4386076504 @default.
- W4385781682 doi "https://doi.org/10.1016/j.ijleo.2023.171251" @default.
- W4385781682 hasPublicationYear "2023" @default.
- W4385781682 type Work @default.
- W4385781682 citedByCount "0" @default.
- W4385781682 crossrefType "journal-article" @default.
- W4385781682 hasAuthorship W4385781682A5056425792 @default.
- W4385781682 hasAuthorship W4385781682A5060099050 @default.
- W4385781682 hasAuthorship W4385781682A5068675549 @default.
- W4385781682 hasAuthorship W4385781682A5070412652 @default.
- W4385781682 hasAuthorship W4385781682A5086585682 @default.
- W4385781682 hasAuthorship W4385781682A5089572482 @default.
- W4385781682 hasConcept C11413529 @default.
- W4385781682 hasConcept C115961682 @default.
- W4385781682 hasConcept C138885662 @default.
- W4385781682 hasConcept C153180895 @default.
- W4385781682 hasConcept C154945302 @default.
- W4385781682 hasConcept C155512373 @default.
- W4385781682 hasConcept C158525013 @default.
- W4385781682 hasConcept C160633673 @default.
- W4385781682 hasConcept C197129107 @default.
- W4385781682 hasConcept C23123220 @default.
- W4385781682 hasConcept C2776401178 @default.
- W4385781682 hasConcept C31972630 @default.
- W4385781682 hasConcept C41008148 @default.
- W4385781682 hasConcept C41895202 @default.
- W4385781682 hasConcept C69744172 @default.
- W4385781682 hasConceptScore W4385781682C11413529 @default.
- W4385781682 hasConceptScore W4385781682C115961682 @default.
- W4385781682 hasConceptScore W4385781682C138885662 @default.
- W4385781682 hasConceptScore W4385781682C153180895 @default.
- W4385781682 hasConceptScore W4385781682C154945302 @default.
- W4385781682 hasConceptScore W4385781682C155512373 @default.
- W4385781682 hasConceptScore W4385781682C158525013 @default.
- W4385781682 hasConceptScore W4385781682C160633673 @default.
- W4385781682 hasConceptScore W4385781682C197129107 @default.
- W4385781682 hasConceptScore W4385781682C23123220 @default.
- W4385781682 hasConceptScore W4385781682C2776401178 @default.
- W4385781682 hasConceptScore W4385781682C31972630 @default.
- W4385781682 hasConceptScore W4385781682C41008148 @default.
- W4385781682 hasConceptScore W4385781682C41895202 @default.
- W4385781682 hasConceptScore W4385781682C69744172 @default.
- W4385781682 hasLocation W43857816821 @default.
- W4385781682 hasOpenAccess W4385781682 @default.
- W4385781682 hasPrimaryLocation W43857816821 @default.
- W4385781682 hasRelatedWork W1490651872 @default.
- W4385781682 hasRelatedWork W1750358731 @default.
- W4385781682 hasRelatedWork W2139242969 @default.
- W4385781682 hasRelatedWork W2204403038 @default.
- W4385781682 hasRelatedWork W2350422455 @default.