FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285105199> ?p ?o ?g. }

• W4285105199 endingPage "14" @default.
• W4285105199 startingPage "1" @default.
• W4285105199 abstract "Images captured in low-light environments often suffer from issues related to dark illumination and damaged details, which results in poor visibility. To address these problems, existing methods have attempted to enhance the visibility of low-light images using convolutional neural networks (CNNs). However, due to the insufficient consideration of crucial features such as illumination and edge details, most of them yield unnatural illumination and blurry details. In this work, to fully exploit these features, we present a detailed analysis of the illumination and edge features of low-light images, observing that the frequency components of these two features are considerably different. Therefore, we explore the frequency distributions of the feature maps extracted from different layers of a CNN model and try to seek the best representation for the illumination and edge information. Based on this, we present a hierarchical feature mining network (HFMNet) that extracts illumination and edge features in different network layers. Specifically, we build a feature mining attention (FMA) module combined with a hierarchical supervised loss to mine crucial features in appropriate network layer. Since deep hierarchical supervision tends to cause overfitting, we introduce an unpaired adversarial loss for improving the generality of the enhancement model. Through extensive experiments and analysis, we demonstrate the advantages of the proposed network, which achieves state-of-the-art performance in terms of image quality." @default.
• W4285105199 created "2022-07-14" @default.
• W4285105199 creator A5026109629 @default.
• W4285105199 creator A5035108397 @default.
• W4285105199 creator A5037592037 @default.
• W4285105199 creator A5039480817 @default.
• W4285105199 creator A5053994118 @default.
• W4285105199 creator A5055415805 @default.
• W4285105199 creator A5067011395 @default.
• W4285105199 date "2022-01-01" @default.
• W4285105199 modified "2023-10-14" @default.
• W4285105199 title "HFMNet: Hierarchical Feature Mining Network for Low-Light Image Enhancement" @default.
• W4285105199 cites W1580436348 @default.
• W4285105199 cites W1973207880 @default.
• W4285105199 cites W2001412060 @default.
• W4285105199 cites W2054814429 @default.
• W4285105199 cites W2082195868 @default.
• W4285105199 cites W2102166818 @default.
• W4285105199 cites W2116973876 @default.
• W4285105199 cites W2133665775 @default.
• W4285105199 cites W2146439264 @default.
• W4285105199 cites W2150721269 @default.
• W4285105199 cites W2159269332 @default.
• W4285105199 cites W2254039850 @default.
• W4285105199 cites W2412926690 @default.
• W4285105199 cites W2468596194 @default.
• W4285105199 cites W2562637781 @default.
• W4285105199 cites W2566376500 @default.
• W4285105199 cites W2593414223 @default.
• W4285105199 cites W2607202125 @default.
• W4285105199 cites W2766802800 @default.
• W4285105199 cites W2791043287 @default.
• W4285105199 cites W2791710889 @default.
• W4285105199 cites W2886690835 @default.
• W4285105199 cites W2948354154 @default.
• W4285105199 cites W2955414824 @default.
• W4285105199 cites W2981718299 @default.
• W4285105199 cites W2986556279 @default.
• W4285105199 cites W2998131124 @default.
• W4285105199 cites W3003838261 @default.
• W4285105199 cites W3016748520 @default.
• W4285105199 cites W3034347506 @default.
• W4285105199 cites W3035022492 @default.
• W4285105199 cites W3042993386 @default.
• W4285105199 cites W3083040138 @default.
• W4285105199 cites W3100618669 @default.
• W4285105199 cites W3107113662 @default.
• W4285105199 cites W3124459155 @default.
• W4285105199 cites W3131451942 @default.
• W4285105199 cites W3134649899 @default.
• W4285105199 cites W3154997553 @default.
• W4285105199 cites W3158777120 @default.
• W4285105199 cites W3173114505 @default.
• W4285105199 cites W3173269149 @default.
• W4285105199 cites W3173515046 @default.
• W4285105199 cites W3174792937 @default.
• W4285105199 cites W3176636832 @default.
• W4285105199 cites W3178960106 @default.
• W4285105199 cites W4205194854 @default.
• W4285105199 cites W4205282138 @default.
• W4285105199 cites W4205610425 @default.
• W4285105199 cites W4210407621 @default.
• W4285105199 doi "https://doi.org/10.1109/tim.2022.3181280" @default.
• W4285105199 hasPublicationYear "2022" @default.
• W4285105199 type Work @default.
• W4285105199 citedByCount "6" @default.
• W4285105199 countsByYear W42851051992023 @default.
• W4285105199 crossrefType "journal-article" @default.
• W4285105199 hasAuthorship W4285105199A5026109629 @default.
• W4285105199 hasAuthorship W4285105199A5035108397 @default.
• W4285105199 hasAuthorship W4285105199A5037592037 @default.
• W4285105199 hasAuthorship W4285105199A5039480817 @default.
• W4285105199 hasAuthorship W4285105199A5053994118 @default.
• W4285105199 hasAuthorship W4285105199A5055415805 @default.
• W4285105199 hasAuthorship W4285105199A5067011395 @default.
• W4285105199 hasConcept C115961682 @default.
• W4285105199 hasConcept C120665830 @default.
• W4285105199 hasConcept C121332964 @default.
• W4285105199 hasConcept C123403432 @default.
• W4285105199 hasConcept C138885662 @default.
• W4285105199 hasConcept C153180895 @default.
• W4285105199 hasConcept C154945302 @default.
• W4285105199 hasConcept C162307627 @default.
• W4285105199 hasConcept C165696696 @default.
• W4285105199 hasConcept C17744445 @default.
• W4285105199 hasConcept C199539241 @default.
• W4285105199 hasConcept C22019652 @default.
• W4285105199 hasConcept C2776359362 @default.
• W4285105199 hasConcept C2776401178 @default.
• W4285105199 hasConcept C31972630 @default.
• W4285105199 hasConcept C38652104 @default.
• W4285105199 hasConcept C41008148 @default.
• W4285105199 hasConcept C41895202 @default.
• W4285105199 hasConcept C50644808 @default.
• W4285105199 hasConcept C52622490 @default.
• W4285105199 hasConcept C81363708 @default.
• W4285105199 hasConcept C94625758 @default.
• W4285105199 hasConceptScore W4285105199C115961682 @default.

• next