Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387212871> ?p ?o ?g. }
- W4387212871 endingPage "104926" @default.
- W4387212871 startingPage "104926" @default.
- W4387212871 abstract "Existing deep learning-based fusion methods usually model local information through convolution operation or global contexts via self-attention mechanism. This serial scheme discards the local features during globality modeling, or vice versa, which may generate limited fusion performance. To tackle this issue, we introduce a mixed-frequency hierarchical guided learning network, or FreqFuse for short. More specifically, we first design a parallel frequency mixer through a channel splitting mechanism, including max-pooling and self-attention paths, to learn both high and low-frequency information. The mixer can provide more comprehensive features within a wide frequency range compared with a single dependency. Second, we develop a dual-Transformer integration module to guide fusion progress. The assigned weights are calculated by cross-token and cross-channel Transformer, which are used to measure the activity levels of source images and preserve their modality characteristics in the intermediate fused features. On this basis, we build a hierarchical guidance decoder to reconstruct a final fusion image. The cross-scale mixed-frequency features are reused to gradually optimize the activity levels of different modality images, and promote the fused result to be highly informative and strongly characterized. We benchmark the proposed FreqFuse on different datasets, and experimental results demonstrate that it achieves impressive performance compared with other methods." @default.
- W4387212871 created "2023-10-01" @default.
- W4387212871 creator A5017900179 @default.
- W4387212871 creator A5018091137 @default.
- W4387212871 creator A5020834943 @default.
- W4387212871 creator A5030604432 @default.
- W4387212871 creator A5039137094 @default.
- W4387212871 date "2023-12-01" @default.
- W4387212871 modified "2023-10-18" @default.
- W4387212871 title "Infrared and visible image fusion via mixed-frequency hierarchical guided learning" @default.
- W4387212871 cites W1964641132 @default.
- W4387212871 cites W2054273865 @default.
- W4387212871 cites W2059193044 @default.
- W4387212871 cites W2091484864 @default.
- W4387212871 cites W2153777140 @default.
- W4387212871 cites W2179019672 @default.
- W4387212871 cites W2589745805 @default.
- W4387212871 cites W2610070095 @default.
- W4387212871 cites W2624240493 @default.
- W4387212871 cites W2912147220 @default.
- W4387212871 cites W2963787388 @default.
- W4387212871 cites W2971071255 @default.
- W4387212871 cites W2997281059 @default.
- W4387212871 cites W2998012573 @default.
- W4387212871 cites W3007891240 @default.
- W4387212871 cites W3011768656 @default.
- W4387212871 cites W3023203534 @default.
- W4387212871 cites W3030921250 @default.
- W4387212871 cites W3105639468 @default.
- W4387212871 cites W3133700567 @default.
- W4387212871 cites W3138516171 @default.
- W4387212871 cites W3143068962 @default.
- W4387212871 cites W3171757599 @default.
- W4387212871 cites W3194077607 @default.
- W4387212871 cites W3208126581 @default.
- W4387212871 cites W4210895834 @default.
- W4387212871 cites W4220893768 @default.
- W4387212871 cites W4282559325 @default.
- W4387212871 cites W4283732315 @default.
- W4387212871 cites W4286361941 @default.
- W4387212871 cites W4312737473 @default.
- W4387212871 cites W4313555022 @default.
- W4387212871 cites W4315652215 @default.
- W4387212871 cites W4317936332 @default.
- W4387212871 cites W4376131895 @default.
- W4387212871 doi "https://doi.org/10.1016/j.infrared.2023.104926" @default.
- W4387212871 hasPublicationYear "2023" @default.
- W4387212871 type Work @default.
- W4387212871 citedByCount "0" @default.
- W4387212871 crossrefType "journal-article" @default.
- W4387212871 hasAuthorship W4387212871A5017900179 @default.
- W4387212871 hasAuthorship W4387212871A5018091137 @default.
- W4387212871 hasAuthorship W4387212871A5020834943 @default.
- W4387212871 hasAuthorship W4387212871A5030604432 @default.
- W4387212871 hasAuthorship W4387212871A5039137094 @default.
- W4387212871 hasConcept C108583219 @default.
- W4387212871 hasConcept C115961682 @default.
- W4387212871 hasConcept C121332964 @default.
- W4387212871 hasConcept C13280743 @default.
- W4387212871 hasConcept C138885662 @default.
- W4387212871 hasConcept C153180895 @default.
- W4387212871 hasConcept C154945302 @default.
- W4387212871 hasConcept C158525013 @default.
- W4387212871 hasConcept C165801399 @default.
- W4387212871 hasConcept C185798385 @default.
- W4387212871 hasConcept C205649164 @default.
- W4387212871 hasConcept C41008148 @default.
- W4387212871 hasConcept C41895202 @default.
- W4387212871 hasConcept C62520636 @default.
- W4387212871 hasConcept C66322947 @default.
- W4387212871 hasConcept C69744172 @default.
- W4387212871 hasConcept C70437156 @default.
- W4387212871 hasConceptScore W4387212871C108583219 @default.
- W4387212871 hasConceptScore W4387212871C115961682 @default.
- W4387212871 hasConceptScore W4387212871C121332964 @default.
- W4387212871 hasConceptScore W4387212871C13280743 @default.
- W4387212871 hasConceptScore W4387212871C138885662 @default.
- W4387212871 hasConceptScore W4387212871C153180895 @default.
- W4387212871 hasConceptScore W4387212871C154945302 @default.
- W4387212871 hasConceptScore W4387212871C158525013 @default.
- W4387212871 hasConceptScore W4387212871C165801399 @default.
- W4387212871 hasConceptScore W4387212871C185798385 @default.
- W4387212871 hasConceptScore W4387212871C205649164 @default.
- W4387212871 hasConceptScore W4387212871C41008148 @default.
- W4387212871 hasConceptScore W4387212871C41895202 @default.
- W4387212871 hasConceptScore W4387212871C62520636 @default.
- W4387212871 hasConceptScore W4387212871C66322947 @default.
- W4387212871 hasConceptScore W4387212871C69744172 @default.
- W4387212871 hasConceptScore W4387212871C70437156 @default.
- W4387212871 hasLocation W43872128711 @default.
- W4387212871 hasOpenAccess W4387212871 @default.
- W4387212871 hasPrimaryLocation W43872128711 @default.
- W4387212871 hasRelatedWork W1490651872 @default.
- W4387212871 hasRelatedWork W1750358731 @default.
- W4387212871 hasRelatedWork W2139242969 @default.
- W4387212871 hasRelatedWork W2204403038 @default.
- W4387212871 hasRelatedWork W2350422455 @default.
- W4387212871 hasRelatedWork W2370195708 @default.