Matches in SemOpenAlex for { <https://semopenalex.org/work/W3043630312> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3043630312 endingPage "4806" @default.
- W3043630312 startingPage "4806" @default.
- W3043630312 abstract "For more than a decade, both academia and industry have focused attention on the computer vision and in particular the computational color constancy (CVCC). The CVCC is used as a fundamental preprocessing task in a wide range of computer vision applications. While our human visual system (HVS) has the innate ability to perceive constant surface colors of objects under varying illumination spectra, the computer vision is facing the color constancy challenge in nature. Accordingly, this article proposes novel convolutional neural network (CNN) architecture based on the residual neural network which consists of pre-activation, atrous or dilated convolution and batch normalization. The proposed network can automatically decide what to learn from input image data and how to pool without supervision. When receiving input image data, the proposed network crops each image into image patches prior to training. Once the network begins learning, local semantic information is automatically extracted from the image patches and fed to its novel pooling layer. As a result of the semantic pooling, a weighted map or a mask is generated. Simultaneously, the extracted information is estimated and combined to form global information during training. The use of the novel pooling layer enables the proposed network to distinguish between useful data and noisy data, and thus efficiently remove noisy data during learning and evaluating. The main contribution of the proposed network is taking CVCC to higher accuracy and efficiency by adopting the novel pooling method. The experimental results demonstrate that the proposed network outperforms its conventional counterparts in estimation accuracy." @default.
- W3043630312 created "2020-07-23" @default.
- W3043630312 creator A5018214137 @default.
- W3043630312 creator A5018641732 @default.
- W3043630312 creator A5045054519 @default.
- W3043630312 date "2020-07-13" @default.
- W3043630312 modified "2023-10-10" @default.
- W3043630312 title "CNN-Based Illumination Estimation with Semantic Information" @default.
- W3043630312 cites W1520390271 @default.
- W3043630312 cites W1950407018 @default.
- W3043630312 cites W1966855663 @default.
- W3043630312 cites W1990309126 @default.
- W3043630312 cites W2052090926 @default.
- W3043630312 cites W2068294844 @default.
- W3043630312 cites W2076205488 @default.
- W3043630312 cites W2088828956 @default.
- W3043630312 cites W2090412934 @default.
- W3043630312 cites W2101752850 @default.
- W3043630312 cites W2111963040 @default.
- W3043630312 cites W2139698815 @default.
- W3043630312 cites W2147933509 @default.
- W3043630312 cites W2154264220 @default.
- W3043630312 cites W2756472722 @default.
- W3043630312 cites W2916633721 @default.
- W3043630312 cites W2946977371 @default.
- W3043630312 doi "https://doi.org/10.3390/app10144806" @default.
- W3043630312 hasPublicationYear "2020" @default.
- W3043630312 type Work @default.
- W3043630312 sameAs 3043630312 @default.
- W3043630312 citedByCount "13" @default.
- W3043630312 countsByYear W30436303122020 @default.
- W3043630312 countsByYear W30436303122021 @default.
- W3043630312 countsByYear W30436303122022 @default.
- W3043630312 countsByYear W30436303122023 @default.
- W3043630312 crossrefType "journal-article" @default.
- W3043630312 hasAuthorship W3043630312A5018214137 @default.
- W3043630312 hasAuthorship W3043630312A5018641732 @default.
- W3043630312 hasAuthorship W3043630312A5045054519 @default.
- W3043630312 hasBestOaLocation W30436303121 @default.
- W3043630312 hasConcept C11413529 @default.
- W3043630312 hasConcept C115961682 @default.
- W3043630312 hasConcept C153180895 @default.
- W3043630312 hasConcept C154945302 @default.
- W3043630312 hasConcept C155512373 @default.
- W3043630312 hasConcept C187888035 @default.
- W3043630312 hasConcept C31972630 @default.
- W3043630312 hasConcept C34736171 @default.
- W3043630312 hasConcept C41008148 @default.
- W3043630312 hasConcept C50644808 @default.
- W3043630312 hasConcept C70437156 @default.
- W3043630312 hasConcept C81363708 @default.
- W3043630312 hasConceptScore W3043630312C11413529 @default.
- W3043630312 hasConceptScore W3043630312C115961682 @default.
- W3043630312 hasConceptScore W3043630312C153180895 @default.
- W3043630312 hasConceptScore W3043630312C154945302 @default.
- W3043630312 hasConceptScore W3043630312C155512373 @default.
- W3043630312 hasConceptScore W3043630312C187888035 @default.
- W3043630312 hasConceptScore W3043630312C31972630 @default.
- W3043630312 hasConceptScore W3043630312C34736171 @default.
- W3043630312 hasConceptScore W3043630312C41008148 @default.
- W3043630312 hasConceptScore W3043630312C50644808 @default.
- W3043630312 hasConceptScore W3043630312C70437156 @default.
- W3043630312 hasConceptScore W3043630312C81363708 @default.
- W3043630312 hasIssue "14" @default.
- W3043630312 hasLocation W30436303121 @default.
- W3043630312 hasLocation W30436303122 @default.
- W3043630312 hasOpenAccess W3043630312 @default.
- W3043630312 hasPrimaryLocation W30436303121 @default.
- W3043630312 hasRelatedWork W147410782 @default.
- W3043630312 hasRelatedWork W2152352598 @default.
- W3043630312 hasRelatedWork W2626256601 @default.
- W3043630312 hasRelatedWork W2810679507 @default.
- W3043630312 hasRelatedWork W2900413183 @default.
- W3043630312 hasRelatedWork W2953234277 @default.
- W3043630312 hasRelatedWork W3022252430 @default.
- W3043630312 hasRelatedWork W3103989898 @default.
- W3043630312 hasRelatedWork W4287804464 @default.
- W3043630312 hasRelatedWork W803346624 @default.
- W3043630312 hasVolume "10" @default.
- W3043630312 isParatext "false" @default.
- W3043630312 isRetracted "false" @default.
- W3043630312 magId "3043630312" @default.
- W3043630312 workType "article" @default.