Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384703208> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4384703208 abstract "Deep features of convolutional neural networks (CNNs), designed for high-level computer vision tasks such as object detection, have been shown to be also effective for image quality assessment (IQA). This motivates further investigations to understand why CNNs are good IQA estimators and, in a broader sense, whether a correspondence exists between CNN's processing stages and the hierarchical mechanism of the human visual system (HVS). In this paper, we stimulate CNNs with a new family of maximally-regular textures to investigate if higher areas of the visual cortex can be approximated within the CNN layers. The results show interesting correspondence between CNNs and the visual cortex, suggesting that these frameworks might be able to serve as suitable baseline candidates for developing a new generation of quality metrics that better replicate the complex stages of the HVS. Developing such IQA models needs in-depth research into the mechanism of the HVS and designing CNNs with better quality-aware feature encoding. As an initial step toward this goal, we established new criteria for improving the performance of pre-trained networks in quality assessment applications by leveraging texture sensitivity. The outcomes illustrate that our feature map weighting and neuron selection criteria could improve the IQA task." @default.
- W4384703208 created "2023-07-20" @default.
- W4384703208 creator A5034083500 @default.
- W4384703208 creator A5064520759 @default.
- W4384703208 date "2023-06-20" @default.
- W4384703208 modified "2023-09-30" @default.
- W4384703208 title "On the Correspondence between Human Vision and Convolutional Neural Networks: A Visual Quality Assessment Perspective" @default.
- W4384703208 cites W1832771320 @default.
- W4384703208 cites W1974013408 @default.
- W4384703208 cites W1992480897 @default.
- W4384703208 cites W2015196405 @default.
- W4384703208 cites W2116360511 @default.
- W4384703208 cites W2127006916 @default.
- W4384703208 cites W2133665775 @default.
- W4384703208 cites W2141983208 @default.
- W4384703208 cites W2171349048 @default.
- W4384703208 cites W2194775991 @default.
- W4384703208 cites W2411961892 @default.
- W4384703208 cites W2571611310 @default.
- W4384703208 cites W2766207481 @default.
- W4384703208 cites W2931290242 @default.
- W4384703208 cites W2962785568 @default.
- W4384703208 cites W3044382929 @default.
- W4384703208 cites W3138218344 @default.
- W4384703208 cites W3190691568 @default.
- W4384703208 cites W4313398726 @default.
- W4384703208 doi "https://doi.org/10.1109/qomex58391.2023.10178580" @default.
- W4384703208 hasPublicationYear "2023" @default.
- W4384703208 type Work @default.
- W4384703208 citedByCount "0" @default.
- W4384703208 crossrefType "proceedings-article" @default.
- W4384703208 hasAuthorship W4384703208A5034083500 @default.
- W4384703208 hasAuthorship W4384703208A5064520759 @default.
- W4384703208 hasConcept C111472728 @default.
- W4384703208 hasConcept C115961682 @default.
- W4384703208 hasConcept C119857082 @default.
- W4384703208 hasConcept C126838900 @default.
- W4384703208 hasConcept C138885662 @default.
- W4384703208 hasConcept C153180895 @default.
- W4384703208 hasConcept C154945302 @default.
- W4384703208 hasConcept C15744967 @default.
- W4384703208 hasConcept C160086991 @default.
- W4384703208 hasConcept C169760540 @default.
- W4384703208 hasConcept C183115368 @default.
- W4384703208 hasConcept C2776401178 @default.
- W4384703208 hasConcept C2779345533 @default.
- W4384703208 hasConcept C2779530757 @default.
- W4384703208 hasConcept C41008148 @default.
- W4384703208 hasConcept C41895202 @default.
- W4384703208 hasConcept C52622490 @default.
- W4384703208 hasConcept C71924100 @default.
- W4384703208 hasConcept C81363708 @default.
- W4384703208 hasConceptScore W4384703208C111472728 @default.
- W4384703208 hasConceptScore W4384703208C115961682 @default.
- W4384703208 hasConceptScore W4384703208C119857082 @default.
- W4384703208 hasConceptScore W4384703208C126838900 @default.
- W4384703208 hasConceptScore W4384703208C138885662 @default.
- W4384703208 hasConceptScore W4384703208C153180895 @default.
- W4384703208 hasConceptScore W4384703208C154945302 @default.
- W4384703208 hasConceptScore W4384703208C15744967 @default.
- W4384703208 hasConceptScore W4384703208C160086991 @default.
- W4384703208 hasConceptScore W4384703208C169760540 @default.
- W4384703208 hasConceptScore W4384703208C183115368 @default.
- W4384703208 hasConceptScore W4384703208C2776401178 @default.
- W4384703208 hasConceptScore W4384703208C2779345533 @default.
- W4384703208 hasConceptScore W4384703208C2779530757 @default.
- W4384703208 hasConceptScore W4384703208C41008148 @default.
- W4384703208 hasConceptScore W4384703208C41895202 @default.
- W4384703208 hasConceptScore W4384703208C52622490 @default.
- W4384703208 hasConceptScore W4384703208C71924100 @default.
- W4384703208 hasConceptScore W4384703208C81363708 @default.
- W4384703208 hasLocation W43847032081 @default.
- W4384703208 hasOpenAccess W4384703208 @default.
- W4384703208 hasPrimaryLocation W43847032081 @default.
- W4384703208 hasRelatedWork W2059299633 @default.
- W4384703208 hasRelatedWork W2546942002 @default.
- W4384703208 hasRelatedWork W2732542196 @default.
- W4384703208 hasRelatedWork W2760085659 @default.
- W4384703208 hasRelatedWork W2767651786 @default.
- W4384703208 hasRelatedWork W2940977206 @default.
- W4384703208 hasRelatedWork W2977314777 @default.
- W4384703208 hasRelatedWork W2995914718 @default.
- W4384703208 hasRelatedWork W3023331843 @default.
- W4384703208 hasRelatedWork W3156786002 @default.
- W4384703208 isParatext "false" @default.
- W4384703208 isRetracted "false" @default.
- W4384703208 workType "article" @default.