FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202581966> ?p ?o ?g. }

• W3202581966 abstract "Nowadays, methods based on deep learning have achieved state-of-the-art performance in image quality assessment (IQA). Many efforts have been made to design convolutional neural network (CNN) for IQA. However, current CNN-based methods mainly have the following shortcomings. (1) CNN-based methods usually segment the image into image patches of the same size for data enhancement, which cannot retain both local spatial information and global spatial information of images with large differences in resolution. (2) Most CNN-based methods input all image patches of the entire image into CNN and assign the image patches the same quality score as the entire image, ignoring the difference in the attention of the human visual system (HVS) to different regions of the image. (3) CNN-based methods design neural network structures with the same channel weight without considering the difference in correlation between different image channels and the key information of image patches. Thus, we propose a multi-scale CNN-based model assisted with visual saliency, which we call MS-SECNN in this paper. We fuse two single-scale CNNs into a multi-scale CNN through a fully connected layer. The Squeeze and Excitation (SE) module is embedded to each single-scale CNN to assign corresponding weight to each image channel. Moreover, we select the image patches input to the multi-scale CNN according to the visual saliency map. Experiments results validate the effectiveness of our proposed method compared to typical full-reference (FR) IQA methods and state-of-the-art no-reference (NR) IQA methods. Our code and two self-built datasets are publicly available <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup>" @default.
• W3202581966 created "2021-10-11" @default.
• W3202581966 creator A5017254378 @default.
• W3202581966 creator A5040335415 @default.
• W3202581966 creator A5090793360 @default.
• W3202581966 date "2021-07-18" @default.
• W3202581966 modified "2023-09-27" @default.
• W3202581966 title "No-reference Image Quality Assessment Based on Multi-scale Convolutional Neural Network Assisted with Visual Saliency" @default.
• W3202581966 cites W1982471090 @default.
• W3202581966 cites W2046119925 @default.
• W3202581966 cites W2061513831 @default.
• W3202581966 cites W2063360098 @default.
• W3202581966 cites W2071346414 @default.
• W3202581966 cites W2073623229 @default.
• W3202581966 cites W2086708275 @default.
• W3202581966 cites W2111425436 @default.
• W3202581966 cites W2115368080 @default.
• W3202581966 cites W2124562516 @default.
• W3202581966 cites W2133665775 @default.
• W3202581966 cites W2138088051 @default.
• W3202581966 cites W2141983208 @default.
• W3202581966 cites W2161907179 @default.
• W3202581966 cites W2162220380 @default.
• W3202581966 cites W2162692770 @default.
• W3202581966 cites W2163370434 @default.
• W3202581966 cites W2171220523 @default.
• W3202581966 cites W2294857031 @default.
• W3202581966 cites W2509123681 @default.
• W3202581966 cites W2518488994 @default.
• W3202581966 cites W2556068545 @default.
• W3202581966 cites W2566149141 @default.
• W3202581966 cites W2568628164 @default.
• W3202581966 cites W2572961056 @default.
• W3202581966 cites W2616017856 @default.
• W3202581966 cites W2749468216 @default.
• W3202581966 cites W2761499647 @default.
• W3202581966 cites W2792845633 @default.
• W3202581966 cites W2793788258 @default.
• W3202581966 cites W2807793257 @default.
• W3202581966 cites W2889592295 @default.
• W3202581966 cites W2902011469 @default.
• W3202581966 cites W4239147634 @default.
• W3202581966 cites W4247049427 @default.
• W3202581966 cites W874645128 @default.
• W3202581966 doi "https://doi.org/10.1109/ijcnn52387.2021.9534406" @default.
• W3202581966 hasPublicationYear "2021" @default.
• W3202581966 type Work @default.
• W3202581966 sameAs 3202581966 @default.
• W3202581966 citedByCount "1" @default.
• W3202581966 countsByYear W32025819662022 @default.
• W3202581966 crossrefType "proceedings-article" @default.
• W3202581966 hasAuthorship W3202581966A5017254378 @default.
• W3202581966 hasAuthorship W3202581966A5040335415 @default.
• W3202581966 hasAuthorship W3202581966A5090793360 @default.
• W3202581966 hasConcept C108583219 @default.
• W3202581966 hasConcept C115961682 @default.
• W3202581966 hasConcept C119599485 @default.
• W3202581966 hasConcept C121332964 @default.
• W3202581966 hasConcept C127162648 @default.
• W3202581966 hasConcept C127413603 @default.
• W3202581966 hasConcept C141353440 @default.
• W3202581966 hasConcept C153180895 @default.
• W3202581966 hasConcept C154945302 @default.
• W3202581966 hasConcept C160086991 @default.
• W3202581966 hasConcept C205372480 @default.
• W3202581966 hasConcept C2778755073 @default.
• W3202581966 hasConcept C31258907 @default.
• W3202581966 hasConcept C31972630 @default.
• W3202581966 hasConcept C36464697 @default.
• W3202581966 hasConcept C41008148 @default.
• W3202581966 hasConcept C55020928 @default.
• W3202581966 hasConcept C62520636 @default.
• W3202581966 hasConcept C81363708 @default.
• W3202581966 hasConceptScore W3202581966C108583219 @default.
• W3202581966 hasConceptScore W3202581966C115961682 @default.
• W3202581966 hasConceptScore W3202581966C119599485 @default.
• W3202581966 hasConceptScore W3202581966C121332964 @default.
• W3202581966 hasConceptScore W3202581966C127162648 @default.
• W3202581966 hasConceptScore W3202581966C127413603 @default.
• W3202581966 hasConceptScore W3202581966C141353440 @default.
• W3202581966 hasConceptScore W3202581966C153180895 @default.
• W3202581966 hasConceptScore W3202581966C154945302 @default.
• W3202581966 hasConceptScore W3202581966C160086991 @default.
• W3202581966 hasConceptScore W3202581966C205372480 @default.
• W3202581966 hasConceptScore W3202581966C2778755073 @default.
• W3202581966 hasConceptScore W3202581966C31258907 @default.
• W3202581966 hasConceptScore W3202581966C31972630 @default.
• W3202581966 hasConceptScore W3202581966C36464697 @default.
• W3202581966 hasConceptScore W3202581966C41008148 @default.
• W3202581966 hasConceptScore W3202581966C55020928 @default.
• W3202581966 hasConceptScore W3202581966C62520636 @default.
• W3202581966 hasConceptScore W3202581966C81363708 @default.
• W3202581966 hasLocation W32025819661 @default.
• W3202581966 hasOpenAccess W3202581966 @default.
• W3202581966 hasPrimaryLocation W32025819661 @default.
• W3202581966 hasRelatedWork W1677446238 @default.
• W3202581966 hasRelatedWork W2184797770 @default.
• W3202581966 hasRelatedWork W2574052219 @default.
• W3202581966 hasRelatedWork W2574066454 @default.
• W3202581966 hasRelatedWork W2738221750 @default.

• next