FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313306370> ?p ?o ?g. }

• W4313306370 endingPage "17" @default.
• W4313306370 startingPage "1" @default.
• W4313306370 abstract "Compressing hyperspectral images (HSIs) into compact representations under the premise of ensuring high-quality reconstruction is an essential task in HSI processing. However, existing compression methods usually encode images by smoothing due to the low-frequency information occupying a prominent component in most images. Consequently, these methods fail to capture sufficient structural information, especially in low bit rates, often causing inferior reconstruction. To address this problem, we propose here an edge-guided hyperspectral compression network, called CENet, to realize high-quality reconstruction. To enhance the structural latent representation ability, the CENet model incorporates an edge extractor neural network into the compression architecture to guide compression optimization by the edge-guided loss. We propose an interactive dual attention module to selectively learn edge features, obtain the most effective edge structure, and avoid additional edge information redundancy at the same time. In the proposed CENet, the edge-guided loss and interactive dual attention module are combined to enhance the comprehensive structure of the latent representation. Concretely, interactive dual attention makes the edge extraction network focus only on moderate boundaries rather than on all edges, which enables savings on the bit rate cost and helps achieve a strong structural representation. As a result, the reconstruction quality is significantly improved. The extensive experiments on seven HSI datasets verify that our model can effectively raise the rate–distortion performance for HSIs of any type or resolution (e.g., yielding an average peak signal-to-noise ratio (PSNR) of 30.59 dB at 0.2382 bpppb, which exceeds the baseline for Chikusei by 10.99%)." @default.
• W4313306370 created "2023-01-06" @default.
• W4313306370 creator A5019685128 @default.
• W4313306370 creator A5025972491 @default.
• W4313306370 creator A5036258937 @default.
• W4313306370 creator A5049671371 @default.
• W4313306370 creator A5077550371 @default.
• W4313306370 date "2023-01-01" @default.
• W4313306370 modified "2023-10-05" @default.
• W4313306370 title "Edge-Guided Hyperspectral Image Compression With Interactive Dual Attention" @default.
• W4313306370 cites W1580389772 @default.
• W4313306370 cites W1596763182 @default.
• W4313306370 cites W1930528368 @default.
• W4313306370 cites W1995875735 @default.
• W4313306370 cites W2010319424 @default.
• W4313306370 cites W2100109944 @default.
• W4313306370 cites W2100495367 @default.
• W4313306370 cites W2120497432 @default.
• W4313306370 cites W2126621530 @default.
• W4313306370 cites W2127205127 @default.
• W4313306370 cites W2133764833 @default.
• W4313306370 cites W2145023731 @default.
• W4313306370 cites W2149359301 @default.
• W4313306370 cites W2152061763 @default.
• W4313306370 cites W2153922636 @default.
• W4313306370 cites W2158548804 @default.
• W4313306370 cites W2161952492 @default.
• W4313306370 cites W2166816543 @default.
• W4313306370 cites W2170023599 @default.
• W4313306370 cites W2558834756 @default.
• W4313306370 cites W2807355972 @default.
• W4313306370 cites W2900537203 @default.
• W4313306370 cites W2911912801 @default.
• W4313306370 cites W2962785568 @default.
• W4313306370 cites W2962891349 @default.
• W4313306370 cites W2963307106 @default.
• W4313306370 cites W2966401131 @default.
• W4313306370 cites W2981613960 @default.
• W4313306370 cites W2990263762 @default.
• W4313306370 cites W2998656915 @default.
• W4313306370 cites W3017971322 @default.
• W4313306370 cites W3034469748 @default.
• W4313306370 cites W3093142463 @default.
• W4313306370 cites W3100975431 @default.
• W4313306370 cites W3102189958 @default.
• W4313306370 cites W3102745911 @default.
• W4313306370 cites W3128077822 @default.
• W4313306370 cites W3129727342 @default.
• W4313306370 cites W3131427579 @default.
• W4313306370 cites W3140627604 @default.
• W4313306370 cites W3171243408 @default.
• W4313306370 cites W3200799048 @default.
• W4313306370 cites W3208382921 @default.
• W4313306370 cites W3216325077 @default.
• W4313306370 cites W4241071816 @default.
• W4313306370 cites W845365781 @default.
• W4313306370 doi "https://doi.org/10.1109/tgrs.2022.3233375" @default.
• W4313306370 hasPublicationYear "2023" @default.
• W4313306370 type Work @default.
• W4313306370 citedByCount "2" @default.
• W4313306370 countsByYear W43133063702023 @default.
• W4313306370 crossrefType "journal-article" @default.
• W4313306370 hasAuthorship W4313306370A5019685128 @default.
• W4313306370 hasAuthorship W4313306370A5025972491 @default.
• W4313306370 hasAuthorship W4313306370A5036258937 @default.
• W4313306370 hasAuthorship W4313306370A5049671371 @default.
• W4313306370 hasAuthorship W4313306370A5077550371 @default.
• W4313306370 hasConcept C115961682 @default.
• W4313306370 hasConcept C13481523 @default.
• W4313306370 hasConcept C153180895 @default.
• W4313306370 hasConcept C154945302 @default.
• W4313306370 hasConcept C159078339 @default.
• W4313306370 hasConcept C162307627 @default.
• W4313306370 hasConcept C31972630 @default.
• W4313306370 hasConcept C3770464 @default.
• W4313306370 hasConcept C41008148 @default.
• W4313306370 hasConcept C78548338 @default.
• W4313306370 hasConcept C9417928 @default.
• W4313306370 hasConceptScore W4313306370C115961682 @default.
• W4313306370 hasConceptScore W4313306370C13481523 @default.
• W4313306370 hasConceptScore W4313306370C153180895 @default.
• W4313306370 hasConceptScore W4313306370C154945302 @default.
• W4313306370 hasConceptScore W4313306370C159078339 @default.
• W4313306370 hasConceptScore W4313306370C162307627 @default.
• W4313306370 hasConceptScore W4313306370C31972630 @default.
• W4313306370 hasConceptScore W4313306370C3770464 @default.
• W4313306370 hasConceptScore W4313306370C41008148 @default.
• W4313306370 hasConceptScore W4313306370C78548338 @default.
• W4313306370 hasConceptScore W4313306370C9417928 @default.
• W4313306370 hasFunder F4320321001 @default.
• W4313306370 hasFunder F4320326938 @default.
• W4313306370 hasLocation W43133063701 @default.
• W4313306370 hasOpenAccess W4313306370 @default.
• W4313306370 hasPrimaryLocation W43133063701 @default.
• W4313306370 hasRelatedWork W1971356997 @default.
• W4313306370 hasRelatedWork W2028628118 @default.
• W4313306370 hasRelatedWork W2036778696 @default.
• W4313306370 hasRelatedWork W2101363760 @default.

• next