Matches in SemOpenAlex for { <https://semopenalex.org/work/W2919112843> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2919112843 endingPage "27" @default.
- W2919112843 startingPage "1" @default.
- W2919112843 abstract "Deep learning has emerged as a powerful tool for feature-driven labeling of datasets. However, for it to be effective, it requires a large and finely labeled training dataset. Precisely labeling a large training dataset is expensive, time-consuming, and error prone. In this article, we present a visually driven deep-learning approach that starts with a coarsely labeled training dataset and iteratively refines the labeling through intuitive interactions that leverage the latent structures of the dataset. Our approach can be used to (a) alleviate the burden of intensive manual labeling that captures the fine nuances in a high-dimensional dataset by simple visual interactions, (b) replace a complicated (and therefore difficult to design) labeling algorithm by a simpler (but coarse) labeling algorithm supplemented by user interaction to refine the labeling, or (c) use low-dimensional features (such as the RGB colors) for coarse labeling and turn to higher-dimensional latent structures that are progressively revealed by deep learning, for fine labeling. We validate our approach through use cases on three high-dimensional datasets and a user study." @default.
- W2919112843 created "2019-03-11" @default.
- W2919112843 creator A5013053394 @default.
- W2919112843 creator A5025024765 @default.
- W2919112843 creator A5050854174 @default.
- W2919112843 creator A5062170963 @default.
- W2919112843 creator A5086440196 @default.
- W2919112843 creator A5089179037 @default.
- W2919112843 creator A5089547246 @default.
- W2919112843 date "2019-03-01" @default.
- W2919112843 modified "2023-10-10" @default.
- W2919112843 title "Enhancing Deep Learning with Visual Interactions" @default.
- W2919112843 cites W1973050785 @default.
- W2919112843 cites W1982729887 @default.
- W2919112843 cites W2002008002 @default.
- W2919112843 cites W2009233867 @default.
- W2919112843 cites W2011316786 @default.
- W2919112843 cites W2029316659 @default.
- W2919112843 cites W2045649112 @default.
- W2919112843 cites W2051088039 @default.
- W2919112843 cites W2053186076 @default.
- W2919112843 cites W2074275752 @default.
- W2919112843 cites W2097308346 @default.
- W2919112843 cites W2118322263 @default.
- W2919112843 cites W2121947440 @default.
- W2919112843 cites W2138621090 @default.
- W2919112843 cites W2152825437 @default.
- W2919112843 cites W2157018954 @default.
- W2919112843 cites W2166923144 @default.
- W2919112843 cites W2506678472 @default.
- W2919112843 cites W2517066960 @default.
- W2919112843 cites W2551180826 @default.
- W2919112843 cites W2793017411 @default.
- W2919112843 cites W66588809 @default.
- W2919112843 doi "https://doi.org/10.1145/3150977" @default.
- W2919112843 hasPublicationYear "2019" @default.
- W2919112843 type Work @default.
- W2919112843 sameAs 2919112843 @default.
- W2919112843 citedByCount "3" @default.
- W2919112843 countsByYear W29191128432021 @default.
- W2919112843 countsByYear W29191128432022 @default.
- W2919112843 countsByYear W29191128432023 @default.
- W2919112843 crossrefType "journal-article" @default.
- W2919112843 hasAuthorship W2919112843A5013053394 @default.
- W2919112843 hasAuthorship W2919112843A5025024765 @default.
- W2919112843 hasAuthorship W2919112843A5050854174 @default.
- W2919112843 hasAuthorship W2919112843A5062170963 @default.
- W2919112843 hasAuthorship W2919112843A5086440196 @default.
- W2919112843 hasAuthorship W2919112843A5089179037 @default.
- W2919112843 hasAuthorship W2919112843A5089547246 @default.
- W2919112843 hasBestOaLocation W29191128431 @default.
- W2919112843 hasConcept C108583219 @default.
- W2919112843 hasConcept C119857082 @default.
- W2919112843 hasConcept C138885662 @default.
- W2919112843 hasConcept C153083717 @default.
- W2919112843 hasConcept C153180895 @default.
- W2919112843 hasConcept C154945302 @default.
- W2919112843 hasConcept C2776145971 @default.
- W2919112843 hasConcept C2776401178 @default.
- W2919112843 hasConcept C41008148 @default.
- W2919112843 hasConcept C41895202 @default.
- W2919112843 hasConcept C82990744 @default.
- W2919112843 hasConceptScore W2919112843C108583219 @default.
- W2919112843 hasConceptScore W2919112843C119857082 @default.
- W2919112843 hasConceptScore W2919112843C138885662 @default.
- W2919112843 hasConceptScore W2919112843C153083717 @default.
- W2919112843 hasConceptScore W2919112843C153180895 @default.
- W2919112843 hasConceptScore W2919112843C154945302 @default.
- W2919112843 hasConceptScore W2919112843C2776145971 @default.
- W2919112843 hasConceptScore W2919112843C2776401178 @default.
- W2919112843 hasConceptScore W2919112843C41008148 @default.
- W2919112843 hasConceptScore W2919112843C41895202 @default.
- W2919112843 hasConceptScore W2919112843C82990744 @default.
- W2919112843 hasIssue "1" @default.
- W2919112843 hasLocation W29191128431 @default.
- W2919112843 hasOpenAccess W2919112843 @default.
- W2919112843 hasPrimaryLocation W29191128431 @default.
- W2919112843 hasRelatedWork W2773120646 @default.
- W2919112843 hasRelatedWork W2919112843 @default.
- W2919112843 hasRelatedWork W3014300295 @default.
- W2919112843 hasRelatedWork W3164822677 @default.
- W2919112843 hasRelatedWork W4205457357 @default.
- W2919112843 hasRelatedWork W4223943233 @default.
- W2919112843 hasRelatedWork W4225161397 @default.
- W2919112843 hasRelatedWork W4299487748 @default.
- W2919112843 hasRelatedWork W4309045103 @default.
- W2919112843 hasRelatedWork W4312200629 @default.
- W2919112843 hasVolume "9" @default.
- W2919112843 isParatext "false" @default.
- W2919112843 isRetracted "false" @default.
- W2919112843 magId "2919112843" @default.
- W2919112843 workType "article" @default.