FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2798986039> ?p ?o ?g. }

• W2798986039 abstract "Finding views with good photo composition is a challenging task for machine learning methods. A key difficulty is the lack of well annotated large scale datasets. Most existing datasets only provide a limited number of annotations for good views, while ignoring the comparative nature of view selection. In this work, we present the first large scale Comparative Photo Composition dataset, which contains over one million comparative view pairs annotated using a cost-effective crowdsourcing workflow. We show that these comparative view annotations are essential for training a robust neural network model for composition. In addition, we propose a novel knowledge transfer framework to train a fast view proposal network, which runs at 75+ FPS and achieves state-of-the-art performance in image cropping and thumbnail generation tasks on three benchmark datasets. The superiority of our method is also demonstrated in a user study on a challenging experiment, where our method significantly outperforms the baseline methods in producing diversified well-composed views." @default.
• W2798986039 created "2018-05-07" @default.
• W2798986039 creator A5024456511 @default.
• W2798986039 creator A5038957718 @default.
• W2798986039 creator A5040218244 @default.
• W2798986039 creator A5047385834 @default.
• W2798986039 creator A5060956547 @default.
• W2798986039 creator A5067580558 @default.
• W2798986039 creator A5076307452 @default.
• W2798986039 date "2018-06-01" @default.
• W2798986039 modified "2023-10-18" @default.
• W2798986039 title "Good View Hunting: Learning Photo Composition from Dense View Pairs" @default.
• W2798986039 cites W1511924373 @default.
• W2798986039 cites W1954873805 @default.
• W2798986039 cites W1975521048 @default.
• W2798986039 cites W1997095443 @default.
• W2798986039 cites W2009678853 @default.
• W2798986039 cites W2013339738 @default.
• W2798986039 cites W2023081159 @default.
• W2798986039 cites W2035214377 @default.
• W2798986039 cites W2046882440 @default.
• W2798986039 cites W2060502770 @default.
• W2798986039 cites W2068730032 @default.
• W2798986039 cites W2078807908 @default.
• W2798986039 cites W2082335776 @default.
• W2798986039 cites W2104915826 @default.
• W2798986039 cites W2108862644 @default.
• W2798986039 cites W2142785776 @default.
• W2798986039 cites W2143331230 @default.
• W2798986039 cites W2154968991 @default.
• W2798986039 cites W2157364932 @default.
• W2798986039 cites W2171398004 @default.
• W2798986039 cites W2211996548 @default.
• W2798986039 cites W2214409633 @default.
• W2798986039 cites W2217895792 @default.
• W2798986039 cites W2467531333 @default.
• W2798986039 cites W2467818129 @default.
• W2798986039 cites W2575939610 @default.
• W2798986039 cites W2580110234 @default.
• W2798986039 cites W2586372171 @default.
• W2798986039 cites W2963312801 @default.
• W2798986039 cites W3103942587 @default.
• W2798986039 cites W4241855926 @default.
• W2798986039 doi "https://doi.org/10.1109/cvpr.2018.00570" @default.
• W2798986039 hasPublicationYear "2018" @default.
• W2798986039 type Work @default.
• W2798986039 sameAs 2798986039 @default.
• W2798986039 citedByCount "51" @default.
• W2798986039 countsByYear W27989860392018 @default.
• W2798986039 countsByYear W27989860392019 @default.
• W2798986039 countsByYear W27989860392020 @default.
• W2798986039 countsByYear W27989860392021 @default.
• W2798986039 countsByYear W27989860392022 @default.
• W2798986039 countsByYear W27989860392023 @default.
• W2798986039 crossrefType "proceedings-article" @default.
• W2798986039 hasAuthorship W2798986039A5024456511 @default.
• W2798986039 hasAuthorship W2798986039A5038957718 @default.
• W2798986039 hasAuthorship W2798986039A5040218244 @default.
• W2798986039 hasAuthorship W2798986039A5047385834 @default.
• W2798986039 hasAuthorship W2798986039A5060956547 @default.
• W2798986039 hasAuthorship W2798986039A5067580558 @default.
• W2798986039 hasAuthorship W2798986039A5076307452 @default.
• W2798986039 hasConcept C111368507 @default.
• W2798986039 hasConcept C115961682 @default.
• W2798986039 hasConcept C119857082 @default.
• W2798986039 hasConcept C121332964 @default.
• W2798986039 hasConcept C12725497 @default.
• W2798986039 hasConcept C127313418 @default.
• W2798986039 hasConcept C13280743 @default.
• W2798986039 hasConcept C136764020 @default.
• W2798986039 hasConcept C138885662 @default.
• W2798986039 hasConcept C150899416 @default.
• W2798986039 hasConcept C154945302 @default.
• W2798986039 hasConcept C160174412 @default.
• W2798986039 hasConcept C162324750 @default.
• W2798986039 hasConcept C177212765 @default.
• W2798986039 hasConcept C185798385 @default.
• W2798986039 hasConcept C187736073 @default.
• W2798986039 hasConcept C205649164 @default.
• W2798986039 hasConcept C23123220 @default.
• W2798986039 hasConcept C26517878 @default.
• W2798986039 hasConcept C2778755073 @default.
• W2798986039 hasConcept C2780451532 @default.
• W2798986039 hasConcept C38652104 @default.
• W2798986039 hasConcept C40231798 @default.
• W2798986039 hasConcept C41008148 @default.
• W2798986039 hasConcept C41895202 @default.
• W2798986039 hasConcept C50644808 @default.
• W2798986039 hasConcept C62230096 @default.
• W2798986039 hasConcept C62520636 @default.
• W2798986039 hasConcept C77088390 @default.
• W2798986039 hasConcept C81917197 @default.
• W2798986039 hasConceptScore W2798986039C111368507 @default.
• W2798986039 hasConceptScore W2798986039C115961682 @default.
• W2798986039 hasConceptScore W2798986039C119857082 @default.
• W2798986039 hasConceptScore W2798986039C121332964 @default.
• W2798986039 hasConceptScore W2798986039C12725497 @default.
• W2798986039 hasConceptScore W2798986039C127313418 @default.
• W2798986039 hasConceptScore W2798986039C13280743 @default.
• W2798986039 hasConceptScore W2798986039C136764020 @default.

• next