FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950489286> ?p ?o ?g. }

• W2950489286 abstract "Despite the recent advances in automatically describing image contents, their applications have been mostly limited to image caption datasets containing natural images (e.g., Flickr 30k, MSCOCO). In this paper, we present a deep learning model to efficiently detect a disease from an image and annotate its contexts (e.g., location, severity and the affected organs). We employ a publicly available radiology dataset of chest x-rays and their reports, and use its image annotations to mine disease names to train convolutional neural networks (CNNs). In doing so, we adopt various regularization techniques to circumvent the large normal-vs-diseased cases bias. Recurrent neural networks (RNNs) are then trained to describe the contexts of a detected disease, based on the deep CNN features. Moreover, we introduce a novel approach to use the weights of the already trained pair of CNN/RNN on the domain-specific image/text dataset, to infer the joint image/text contexts for composite image labeling. Significantly improved image annotation results are demonstrated using the recurrent neural cascade model by taking the joint image/text contexts into account." @default.
• W2950489286 created "2019-06-27" @default.
• W2950489286 creator A5016047550 @default.
• W2950489286 creator A5045227579 @default.
• W2950489286 creator A5046695536 @default.
• W2950489286 creator A5046709245 @default.
• W2950489286 creator A5046764593 @default.
• W2950489286 creator A5050226865 @default.
• W2950489286 date "2016-03-28" @default.
• W2950489286 modified "2023-09-23" @default.
• W2950489286 title "Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation" @default.
• W2950489286 cites W1514535095 @default.
• W2950489286 cites W1527575280 @default.
• W2950489286 cites W1530232666 @default.
• W2950489286 cites W1586939924 @default.
• W2950489286 cites W1686810756 @default.
• W2950489286 cites W1810943226 @default.
• W2950489286 cites W1895577753 @default.
• W2950489286 cites W1897761818 @default.
• W2950489286 cites W1901943601 @default.
• W2950489286 cites W1904365287 @default.
• W2950489286 cites W1905882502 @default.
• W2950489286 cites W1907845728 @default.
• W2950489286 cites W1914581815 @default.
• W2950489286 cites W1924770834 @default.
• W2950489286 cites W1931639407 @default.
• W2950489286 cites W1947481528 @default.
• W2950489286 cites W1951216520 @default.
• W2950489286 cites W1957706851 @default.
• W2950489286 cites W1962480448 @default.
• W2950489286 cites W1969616664 @default.
• W2950489286 cites W1974823213 @default.
• W2950489286 cites W1976806664 @default.
• W2950489286 cites W2015103117 @default.
• W2950489286 cites W2020860763 @default.
• W2950489286 cites W2064675550 @default.
• W2950489286 cites W2065165141 @default.
• W2950489286 cites W2070812954 @default.
• W2950489286 cites W2077554240 @default.
• W2950489286 cites W2080927070 @default.
• W2950489286 cites W2097117768 @default.
• W2950489286 cites W2101105183 @default.
• W2950489286 cites W2101234009 @default.
• W2950489286 cites W2108598243 @default.
• W2950489286 cites W2112264109 @default.
• W2950489286 cites W2114453188 @default.
• W2950489286 cites W2118434577 @default.
• W2950489286 cites W2126384256 @default.
• W2950489286 cites W2133533561 @default.
• W2950489286 cites W2139501017 @default.
• W2950489286 cites W2143612262 @default.
• W2950489286 cites W2144012961 @default.
• W2950489286 cites W2152772232 @default.
• W2950489286 cites W2157331557 @default.
• W2950489286 cites W2159243025 @default.
• W2950489286 cites W2187089797 @default.
• W2950489286 cites W2293575453 @default.
• W2950489286 cites W2407639284 @default.
• W2950489286 cites W2949117887 @default.
• W2950489286 cites W2949888546 @default.
• W2950489286 cites W2953061907 @default.
• W2950489286 cites W2963639714 @default.
• W2950489286 cites W2963911037 @default.
• W2950489286 cites W581956982 @default.
• W2950489286 cites W68733909 @default.
• W2950489286 cites W2010382953 @default.
• W2950489286 doi "https://doi.org/10.48550/arxiv.1603.08486" @default.
• W2950489286 hasPublicationYear "2016" @default.
• W2950489286 type Work @default.
• W2950489286 sameAs 2950489286 @default.
• W2950489286 citedByCount "14" @default.
• W2950489286 countsByYear W29504892862017 @default.
• W2950489286 countsByYear W29504892862018 @default.
• W2950489286 countsByYear W29504892862019 @default.
• W2950489286 countsByYear W29504892862020 @default.
• W2950489286 countsByYear W29504892862021 @default.
• W2950489286 crossrefType "posted-content" @default.
• W2950489286 hasAuthorship W2950489286A5016047550 @default.
• W2950489286 hasAuthorship W2950489286A5045227579 @default.
• W2950489286 hasAuthorship W2950489286A5046695536 @default.
• W2950489286 hasAuthorship W2950489286A5046709245 @default.
• W2950489286 hasAuthorship W2950489286A5046764593 @default.
• W2950489286 hasAuthorship W2950489286A5050226865 @default.
• W2950489286 hasBestOaLocation W29504892861 @default.
• W2950489286 hasConcept C108583219 @default.
• W2950489286 hasConcept C115961682 @default.
• W2950489286 hasConcept C119857082 @default.
• W2950489286 hasConcept C147168706 @default.
• W2950489286 hasConcept C153180895 @default.
• W2950489286 hasConcept C154945302 @default.
• W2950489286 hasConcept C204321447 @default.
• W2950489286 hasConcept C2776135515 @default.
• W2950489286 hasConcept C2776321320 @default.
• W2950489286 hasConcept C41008148 @default.
• W2950489286 hasConcept C50644808 @default.
• W2950489286 hasConcept C81363708 @default.
• W2950489286 hasConceptScore W2950489286C108583219 @default.
• W2950489286 hasConceptScore W2950489286C115961682 @default.
• W2950489286 hasConceptScore W2950489286C119857082 @default.
• W2950489286 hasConceptScore W2950489286C147168706 @default.

• next