Matches in SemOpenAlex for { <https://semopenalex.org/work/W2780077666> ?p ?o ?g. }
- W2780077666 abstract "Despite recent progress, computational visual aesthetic is still challenging. Image cropping, which refers to the removal of unwanted scene areas, is an important step to improve the aesthetic quality of an image. However, it is challenging to evaluate whether cropping leads to aesthetically pleasing results because the assessment is typically subjective. In this paper, we propose a novel cascaded cropping regression (CCR) method to perform image cropping by learning the knowledge from professional photographers. The proposed CCR method improves the convergence speed of the cascaded method, which directly uses random-ferns regressors. In addition, a two-step learning strategy is proposed and used in the CCR method to address the problem of lacking labelled cropping data. Specifically, a deep convolutional neural network (CNN) classifier is first trained on large-scale visual aesthetic datasets. The deep CNN model is then designed to extract features from several image cropping datasets, upon which the cropping bounding boxes are predicted by the proposed CCR method. Experimental results on public image cropping datasets demonstrate that the proposed method significantly outperforms several state-of-the-art image cropping methods." @default.
- W2780077666 created "2018-01-05" @default.
- W2780077666 creator A5006294869 @default.
- W2780077666 creator A5026914509 @default.
- W2780077666 creator A5044594971 @default.
- W2780077666 creator A5048411184 @default.
- W2780077666 creator A5071671012 @default.
- W2780077666 date "2017-12-25" @default.
- W2780077666 modified "2023-09-23" @default.
- W2780077666 title "Automatic Image Cropping for Visual Aesthetic Enhancement Using Deep Neural Networks and Cascaded Regression" @default.
- W2780077666 cites W1511924373 @default.
- W2780077666 cites W1678356000 @default.
- W2780077666 cites W1971616954 @default.
- W2780077666 cites W1976948919 @default.
- W2780077666 cites W1977476420 @default.
- W2780077666 cites W1990937109 @default.
- W2780077666 cites W2001070410 @default.
- W2780077666 cites W2009678853 @default.
- W2780077666 cites W2013339738 @default.
- W2780077666 cites W2017719067 @default.
- W2780077666 cites W2023081159 @default.
- W2780077666 cites W2048835603 @default.
- W2780077666 cites W2052245719 @default.
- W2780077666 cites W2056380823 @default.
- W2780077666 cites W2059283460 @default.
- W2780077666 cites W2060565253 @default.
- W2780077666 cites W2061167180 @default.
- W2780077666 cites W2063948594 @default.
- W2780077666 cites W2082335776 @default.
- W2780077666 cites W2107363596 @default.
- W2780077666 cites W2109255472 @default.
- W2780077666 cites W2129644086 @default.
- W2780077666 cites W2142785776 @default.
- W2780077666 cites W2159624360 @default.
- W2780077666 cites W2165810675 @default.
- W2780077666 cites W2467531333 @default.
- W2780077666 cites W2497173630 @default.
- W2780077666 cites W2586275201 @default.
- W2780077666 cites W2588983561 @default.
- W2780077666 cites W2996076706 @default.
- W2780077666 cites W753012316 @default.
- W2780077666 doi "https://doi.org/10.48550/arxiv.1712.09048" @default.
- W2780077666 hasPublicationYear "2017" @default.
- W2780077666 type Work @default.
- W2780077666 sameAs 2780077666 @default.
- W2780077666 citedByCount "1" @default.
- W2780077666 countsByYear W27800776662019 @default.
- W2780077666 crossrefType "posted-content" @default.
- W2780077666 hasAuthorship W2780077666A5006294869 @default.
- W2780077666 hasAuthorship W2780077666A5026914509 @default.
- W2780077666 hasAuthorship W2780077666A5044594971 @default.
- W2780077666 hasAuthorship W2780077666A5048411184 @default.
- W2780077666 hasAuthorship W2780077666A5071671012 @default.
- W2780077666 hasBestOaLocation W27800776661 @default.
- W2780077666 hasConcept C105795698 @default.
- W2780077666 hasConcept C108583219 @default.
- W2780077666 hasConcept C115961682 @default.
- W2780077666 hasConcept C118518473 @default.
- W2780077666 hasConcept C119857082 @default.
- W2780077666 hasConcept C13558536 @default.
- W2780077666 hasConcept C153180895 @default.
- W2780077666 hasConcept C154945302 @default.
- W2780077666 hasConcept C166957645 @default.
- W2780077666 hasConcept C205649164 @default.
- W2780077666 hasConcept C33923547 @default.
- W2780077666 hasConcept C41008148 @default.
- W2780077666 hasConcept C50644808 @default.
- W2780077666 hasConcept C63584917 @default.
- W2780077666 hasConcept C81363708 @default.
- W2780077666 hasConcept C83546350 @default.
- W2780077666 hasConceptScore W2780077666C105795698 @default.
- W2780077666 hasConceptScore W2780077666C108583219 @default.
- W2780077666 hasConceptScore W2780077666C115961682 @default.
- W2780077666 hasConceptScore W2780077666C118518473 @default.
- W2780077666 hasConceptScore W2780077666C119857082 @default.
- W2780077666 hasConceptScore W2780077666C13558536 @default.
- W2780077666 hasConceptScore W2780077666C153180895 @default.
- W2780077666 hasConceptScore W2780077666C154945302 @default.
- W2780077666 hasConceptScore W2780077666C166957645 @default.
- W2780077666 hasConceptScore W2780077666C205649164 @default.
- W2780077666 hasConceptScore W2780077666C33923547 @default.
- W2780077666 hasConceptScore W2780077666C41008148 @default.
- W2780077666 hasConceptScore W2780077666C50644808 @default.
- W2780077666 hasConceptScore W2780077666C63584917 @default.
- W2780077666 hasConceptScore W2780077666C81363708 @default.
- W2780077666 hasConceptScore W2780077666C83546350 @default.
- W2780077666 hasLocation W27800776661 @default.
- W2780077666 hasOpenAccess W2780077666 @default.
- W2780077666 hasPrimaryLocation W27800776661 @default.
- W2780077666 hasRelatedWork W2337926734 @default.
- W2780077666 hasRelatedWork W2732542196 @default.
- W2780077666 hasRelatedWork W2738221750 @default.
- W2780077666 hasRelatedWork W3021430260 @default.
- W2780077666 hasRelatedWork W3136076031 @default.
- W2780077666 hasRelatedWork W3156786002 @default.
- W2780077666 hasRelatedWork W3186111093 @default.
- W2780077666 hasRelatedWork W4214561993 @default.
- W2780077666 hasRelatedWork W4311257506 @default.
- W2780077666 hasRelatedWork W564581980 @default.
- W2780077666 isParatext "false" @default.