Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313705020> ?p ?o ?g. }
- W4313705020 endingPage "103751" @default.
- W4313705020 startingPage "103751" @default.
- W4313705020 abstract "“Composition” determines the vividness of the image and its narrative power. Current research on image aesthetics implicitly considers simple composition rules, but no reliable composition classification and image optimization method explicitly considers composition rules. The existing composition classification models are not suitable for snapshots. We propose a composition classification model based on spatial-invariant convolutional neural networks (RSTN) with translation invariance and rotation invariance. It enhances the generalization of the model for snapshots or skewed images. Ultimately, the accuracy of the RSTN model improved by 3% over the Baseline to 90.8762%, and the rotation consistency improved by 16.015%. Furthermore, we classify images into three categories based on their sensitivity to editing: skew-sensitive, translation-sensitive, and non-space-sensitive. We design a set of composition optimization strategies for each composition that can effectively adjust the composition to beautify the image." @default.
- W4313705020 created "2023-01-08" @default.
- W4313705020 creator A5028463238 @default.
- W4313705020 creator A5052528110 @default.
- W4313705020 creator A5073349631 @default.
- W4313705020 creator A5073531557 @default.
- W4313705020 creator A5088408781 @default.
- W4313705020 date "2023-02-01" @default.
- W4313705020 modified "2023-09-26" @default.
- W4313705020 title "Spatial-invariant convolutional neural network for photographic composition prediction and automatic correction" @default.
- W4313705020 cites W2003856922 @default.
- W4313705020 cites W2028978183 @default.
- W4313705020 cites W2046882440 @default.
- W4313705020 cites W2082335776 @default.
- W4313705020 cites W2109255472 @default.
- W4313705020 cites W2111632961 @default.
- W4313705020 cites W2194775991 @default.
- W4313705020 cites W2295107390 @default.
- W4313705020 cites W2467531333 @default.
- W4313705020 cites W2586372171 @default.
- W4313705020 cites W2746230666 @default.
- W4313705020 cites W2751782044 @default.
- W4313705020 cites W2766458758 @default.
- W4313705020 cites W2775725209 @default.
- W4313705020 cites W2798986039 @default.
- W4313705020 cites W2807107013 @default.
- W4313705020 cites W2941419932 @default.
- W4313705020 cites W2941860851 @default.
- W4313705020 cites W2963010685 @default.
- W4313705020 cites W2963312801 @default.
- W4313705020 cites W2981548364 @default.
- W4313705020 cites W3186050100 @default.
- W4313705020 doi "https://doi.org/10.1016/j.jvcir.2023.103751" @default.
- W4313705020 hasPublicationYear "2023" @default.
- W4313705020 type Work @default.
- W4313705020 citedByCount "0" @default.
- W4313705020 crossrefType "journal-article" @default.
- W4313705020 hasAuthorship W4313705020A5028463238 @default.
- W4313705020 hasAuthorship W4313705020A5052528110 @default.
- W4313705020 hasAuthorship W4313705020A5073349631 @default.
- W4313705020 hasAuthorship W4313705020A5073531557 @default.
- W4313705020 hasAuthorship W4313705020A5088408781 @default.
- W4313705020 hasConcept C104317684 @default.
- W4313705020 hasConcept C105580179 @default.
- W4313705020 hasConcept C115961682 @default.
- W4313705020 hasConcept C138885662 @default.
- W4313705020 hasConcept C149364088 @default.
- W4313705020 hasConcept C153180895 @default.
- W4313705020 hasConcept C154945302 @default.
- W4313705020 hasConcept C185592680 @default.
- W4313705020 hasConcept C190470478 @default.
- W4313705020 hasConcept C2779757391 @default.
- W4313705020 hasConcept C31972630 @default.
- W4313705020 hasConcept C33923547 @default.
- W4313705020 hasConcept C37914503 @default.
- W4313705020 hasConcept C40231798 @default.
- W4313705020 hasConcept C41008148 @default.
- W4313705020 hasConcept C41895202 @default.
- W4313705020 hasConcept C43711488 @default.
- W4313705020 hasConcept C55493867 @default.
- W4313705020 hasConcept C74050887 @default.
- W4313705020 hasConcept C76155785 @default.
- W4313705020 hasConcept C81363708 @default.
- W4313705020 hasConceptScore W4313705020C104317684 @default.
- W4313705020 hasConceptScore W4313705020C105580179 @default.
- W4313705020 hasConceptScore W4313705020C115961682 @default.
- W4313705020 hasConceptScore W4313705020C138885662 @default.
- W4313705020 hasConceptScore W4313705020C149364088 @default.
- W4313705020 hasConceptScore W4313705020C153180895 @default.
- W4313705020 hasConceptScore W4313705020C154945302 @default.
- W4313705020 hasConceptScore W4313705020C185592680 @default.
- W4313705020 hasConceptScore W4313705020C190470478 @default.
- W4313705020 hasConceptScore W4313705020C2779757391 @default.
- W4313705020 hasConceptScore W4313705020C31972630 @default.
- W4313705020 hasConceptScore W4313705020C33923547 @default.
- W4313705020 hasConceptScore W4313705020C37914503 @default.
- W4313705020 hasConceptScore W4313705020C40231798 @default.
- W4313705020 hasConceptScore W4313705020C41008148 @default.
- W4313705020 hasConceptScore W4313705020C41895202 @default.
- W4313705020 hasConceptScore W4313705020C43711488 @default.
- W4313705020 hasConceptScore W4313705020C55493867 @default.
- W4313705020 hasConceptScore W4313705020C74050887 @default.
- W4313705020 hasConceptScore W4313705020C76155785 @default.
- W4313705020 hasConceptScore W4313705020C81363708 @default.
- W4313705020 hasFunder F4320321001 @default.
- W4313705020 hasFunder F4320323993 @default.
- W4313705020 hasLocation W43137050201 @default.
- W4313705020 hasOpenAccess W4313705020 @default.
- W4313705020 hasPrimaryLocation W43137050201 @default.
- W4313705020 hasRelatedWork W2046133581 @default.
- W4313705020 hasRelatedWork W2091447162 @default.
- W4313705020 hasRelatedWork W2357536448 @default.
- W4313705020 hasRelatedWork W2361114818 @default.
- W4313705020 hasRelatedWork W2366854666 @default.
- W4313705020 hasRelatedWork W2401401198 @default.
- W4313705020 hasRelatedWork W2402395612 @default.
- W4313705020 hasRelatedWork W3044330909 @default.
- W4313705020 hasRelatedWork W3135923011 @default.