Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367694411> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4367694411 abstract "The use of quaternions as a novel tool for color image representation has yielded impressive results in color image processing. By considering the color image as a unified entity rather than separate color space components, quaternions can effectively exploit the strong correlation among the RGB channels, leading to enhanced performance. Especially, color image inpainting tasks are highly beneficial from the application of quaternion matrix completion techniques, in recent years. However, existing quaternion matrix completion methods suffer from two major drawbacks. First, it can be difficult to choose a regularizer that captures the common characteristics of natural images, and sometimes the regularizer that is chosen based on empirical evidence may not be the optimal or efficient option. Second, the optimization process of quaternion matrix completion models is quite challenging because of the non-commutativity of quaternion multiplication. To address the two drawbacks of the existing quaternion matrix completion approaches mentioned above, this paper tends to use an untrained quaternion convolutional neural network (QCNN) to directly generate the completed quaternion matrix. This approach replaces the explicit regularization term in the quaternion matrix completion model with an implicit prior that is learned by the QCNN. Extensive quantitative and qualitative evaluations demonstrate the superiority of the proposed method for color image inpainting compared with some existing quaternion-based and tensor-based methods." @default.
- W4367694411 created "2023-05-03" @default.
- W4367694411 creator A5010571667 @default.
- W4367694411 creator A5016962594 @default.
- W4367694411 creator A5019787502 @default.
- W4367694411 creator A5039110604 @default.
- W4367694411 date "2023-04-30" @default.
- W4367694411 modified "2023-10-16" @default.
- W4367694411 title "Quaternion Matrix Completion Using Untrained Quaternion Convolutional Neural Network for Color Image Inpainting" @default.
- W4367694411 doi "https://doi.org/10.48550/arxiv.2305.00416" @default.
- W4367694411 hasPublicationYear "2023" @default.
- W4367694411 type Work @default.
- W4367694411 citedByCount "0" @default.
- W4367694411 crossrefType "posted-content" @default.
- W4367694411 hasAuthorship W4367694411A5010571667 @default.
- W4367694411 hasAuthorship W4367694411A5016962594 @default.
- W4367694411 hasAuthorship W4367694411A5019787502 @default.
- W4367694411 hasAuthorship W4367694411A5039110604 @default.
- W4367694411 hasBestOaLocation W43676944111 @default.
- W4367694411 hasConcept C106487976 @default.
- W4367694411 hasConcept C11413529 @default.
- W4367694411 hasConcept C115961682 @default.
- W4367694411 hasConcept C11727466 @default.
- W4367694411 hasConcept C142616399 @default.
- W4367694411 hasConcept C154945302 @default.
- W4367694411 hasConcept C159985019 @default.
- W4367694411 hasConcept C192562407 @default.
- W4367694411 hasConcept C200127275 @default.
- W4367694411 hasConcept C2524010 @default.
- W4367694411 hasConcept C2776135515 @default.
- W4367694411 hasConcept C31972630 @default.
- W4367694411 hasConcept C33923547 @default.
- W4367694411 hasConcept C41008148 @default.
- W4367694411 hasConcept C81363708 @default.
- W4367694411 hasConcept C9417928 @default.
- W4367694411 hasConceptScore W4367694411C106487976 @default.
- W4367694411 hasConceptScore W4367694411C11413529 @default.
- W4367694411 hasConceptScore W4367694411C115961682 @default.
- W4367694411 hasConceptScore W4367694411C11727466 @default.
- W4367694411 hasConceptScore W4367694411C142616399 @default.
- W4367694411 hasConceptScore W4367694411C154945302 @default.
- W4367694411 hasConceptScore W4367694411C159985019 @default.
- W4367694411 hasConceptScore W4367694411C192562407 @default.
- W4367694411 hasConceptScore W4367694411C200127275 @default.
- W4367694411 hasConceptScore W4367694411C2524010 @default.
- W4367694411 hasConceptScore W4367694411C2776135515 @default.
- W4367694411 hasConceptScore W4367694411C31972630 @default.
- W4367694411 hasConceptScore W4367694411C33923547 @default.
- W4367694411 hasConceptScore W4367694411C41008148 @default.
- W4367694411 hasConceptScore W4367694411C81363708 @default.
- W4367694411 hasConceptScore W4367694411C9417928 @default.
- W4367694411 hasLocation W43676944111 @default.
- W4367694411 hasOpenAccess W4367694411 @default.
- W4367694411 hasPrimaryLocation W43676944111 @default.
- W4367694411 hasRelatedWork W148995698 @default.
- W4367694411 hasRelatedWork W1533292911 @default.
- W4367694411 hasRelatedWork W2005185696 @default.
- W4367694411 hasRelatedWork W2076843379 @default.
- W4367694411 hasRelatedWork W2362326443 @default.
- W4367694411 hasRelatedWork W2383395053 @default.
- W4367694411 hasRelatedWork W3207471954 @default.
- W4367694411 hasRelatedWork W4292794826 @default.
- W4367694411 hasRelatedWork W4365518851 @default.
- W4367694411 hasRelatedWork W87913359 @default.
- W4367694411 isParatext "false" @default.
- W4367694411 isRetracted "false" @default.
- W4367694411 workType "article" @default.