Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999972022> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2999972022 abstract "Since convolutional neural networks (CNNs) were used in image fusion field, they have showed state-of-the-art quality beyond traditional methods. However, the existing CNN fusion models have a high computational cost and require high memory capacity, which is impractical for embedded applications or mobile platforms. Inspired by the efficiency of the lightweight network architecture of SqueezeNet, MobileNet, and ShuffleNet, we propose a tiny fusion method for image fusion, which significantly decreasing the number of operations and memory needed while retaining the same fusion quality. Extensive experimental results indicate that tiny deep neural network architectures can be designed for real-time image fusion that are well suited for embedded scenarios. To the best of our knowledge, our method is the first lightweight network architecture for image fusion." @default.
- W2999972022 created "2020-01-23" @default.
- W2999972022 creator A5016765078 @default.
- W2999972022 creator A5036031567 @default.
- W2999972022 creator A5063519388 @default.
- W2999972022 creator A5081332468 @default.
- W2999972022 creator A5081893704 @default.
- W2999972022 date "2019-09-01" @default.
- W2999972022 modified "2023-09-23" @default.
- W2999972022 title "Tiny Fusion: Tiny Deep Convolutional Neural Network for Real-time Image Fusion" @default.
- W2999972022 cites W1587659608 @default.
- W2999972022 cites W1965606870 @default.
- W2999972022 cites W1980382026 @default.
- W2999972022 cites W2005682787 @default.
- W2999972022 cites W2040833130 @default.
- W2999972022 cites W2044394856 @default.
- W2999972022 cites W2129112648 @default.
- W2999972022 cites W2170245688 @default.
- W2999972022 cites W2266694576 @default.
- W2999972022 cites W2532801510 @default.
- W2999972022 cites W2552737937 @default.
- W2999972022 cites W2559870345 @default.
- W2999972022 cites W2589745805 @default.
- W2999972022 cites W2610070095 @default.
- W2999972022 cites W2798018774 @default.
- W2999972022 cites W2963163009 @default.
- W2999972022 cites W2963446712 @default.
- W2999972022 cites W2963530785 @default.
- W2999972022 cites W3105639468 @default.
- W2999972022 doi "https://doi.org/10.1109/icicsp48821.2019.8958570" @default.
- W2999972022 hasPublicationYear "2019" @default.
- W2999972022 type Work @default.
- W2999972022 sameAs 2999972022 @default.
- W2999972022 citedByCount "0" @default.
- W2999972022 crossrefType "proceedings-article" @default.
- W2999972022 hasAuthorship W2999972022A5016765078 @default.
- W2999972022 hasAuthorship W2999972022A5036031567 @default.
- W2999972022 hasAuthorship W2999972022A5063519388 @default.
- W2999972022 hasAuthorship W2999972022A5081332468 @default.
- W2999972022 hasAuthorship W2999972022A5081893704 @default.
- W2999972022 hasConcept C108583219 @default.
- W2999972022 hasConcept C115961682 @default.
- W2999972022 hasConcept C138885662 @default.
- W2999972022 hasConcept C154945302 @default.
- W2999972022 hasConcept C158525013 @default.
- W2999972022 hasConcept C202444582 @default.
- W2999972022 hasConcept C31972630 @default.
- W2999972022 hasConcept C33923547 @default.
- W2999972022 hasConcept C41008148 @default.
- W2999972022 hasConcept C41895202 @default.
- W2999972022 hasConcept C50644808 @default.
- W2999972022 hasConcept C55020928 @default.
- W2999972022 hasConcept C69744172 @default.
- W2999972022 hasConcept C81363708 @default.
- W2999972022 hasConcept C9652623 @default.
- W2999972022 hasConceptScore W2999972022C108583219 @default.
- W2999972022 hasConceptScore W2999972022C115961682 @default.
- W2999972022 hasConceptScore W2999972022C138885662 @default.
- W2999972022 hasConceptScore W2999972022C154945302 @default.
- W2999972022 hasConceptScore W2999972022C158525013 @default.
- W2999972022 hasConceptScore W2999972022C202444582 @default.
- W2999972022 hasConceptScore W2999972022C31972630 @default.
- W2999972022 hasConceptScore W2999972022C33923547 @default.
- W2999972022 hasConceptScore W2999972022C41008148 @default.
- W2999972022 hasConceptScore W2999972022C41895202 @default.
- W2999972022 hasConceptScore W2999972022C50644808 @default.
- W2999972022 hasConceptScore W2999972022C55020928 @default.
- W2999972022 hasConceptScore W2999972022C69744172 @default.
- W2999972022 hasConceptScore W2999972022C81363708 @default.
- W2999972022 hasConceptScore W2999972022C9652623 @default.
- W2999972022 hasLocation W29999720221 @default.
- W2999972022 hasOpenAccess W2999972022 @default.
- W2999972022 hasPrimaryLocation W29999720221 @default.
- W2999972022 hasRelatedWork W2011639587 @default.
- W2999972022 hasRelatedWork W2012530243 @default.
- W2999972022 hasRelatedWork W2023497873 @default.
- W2999972022 hasRelatedWork W2048661006 @default.
- W2999972022 hasRelatedWork W2103111580 @default.
- W2999972022 hasRelatedWork W2478884406 @default.
- W2999972022 hasRelatedWork W2573355895 @default.
- W2999972022 hasRelatedWork W2810384904 @default.
- W2999972022 hasRelatedWork W2890217380 @default.
- W2999972022 hasRelatedWork W2920938200 @default.
- W2999972022 isParatext "false" @default.
- W2999972022 isRetracted "false" @default.
- W2999972022 magId "2999972022" @default.
- W2999972022 workType "article" @default.