Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897649600> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2897649600 abstract "Deep learning techniques have been successfully applied to image processing tasks. Nevertheless, these techniques can be sensitive to the occurrence of small training sets, which is commonly faced when model training requires labelled instances. Transfer learning has been adopted to overcome this limitation by leveraging richer information in auxiliary domains to enhance the learning process in a target domain. In this paper, we proposed a new solution for transfer learning to label images (i.e., the target domain) by reusing labelled textual data (i.e., the auxiliary domain). A convolutional encoder is used to find latent features for images, while a probabilistic generative model is used to find semantic topics (traits) for texts. An ensemble of classifiers is then used to predict semantic topics to new input images according to their latent features. Experiments were performed to evaluate whether the latent features in both domains can actually be related and also to verify the use of the predicted semantic topics to classify images. Promising results were achieved compared to different baselines." @default.
- W2897649600 created "2018-10-26" @default.
- W2897649600 creator A5085118013 @default.
- W2897649600 creator A5090325608 @default.
- W2897649600 date "2018-07-01" @default.
- W2897649600 modified "2023-09-27" @default.
- W2897649600 title "Transferring Knowledge From Texts to Images by Combining Deep Semantic Feature Descriptors" @default.
- W2897649600 cites W2007972815 @default.
- W2897649600 cites W2050398567 @default.
- W2897649600 cites W2097117768 @default.
- W2897649600 cites W2098355853 @default.
- W2897649600 cites W2108598243 @default.
- W2897649600 cites W2161381512 @default.
- W2897649600 cites W2194775991 @default.
- W2897649600 cites W2280985394 @default.
- W2897649600 cites W2395579298 @default.
- W2897649600 cites W2523168882 @default.
- W2897649600 doi "https://doi.org/10.1109/ijcnn.2018.8489058" @default.
- W2897649600 hasPublicationYear "2018" @default.
- W2897649600 type Work @default.
- W2897649600 sameAs 2897649600 @default.
- W2897649600 citedByCount "0" @default.
- W2897649600 crossrefType "proceedings-article" @default.
- W2897649600 hasAuthorship W2897649600A5085118013 @default.
- W2897649600 hasAuthorship W2897649600A5090325608 @default.
- W2897649600 hasConcept C108583219 @default.
- W2897649600 hasConcept C111919701 @default.
- W2897649600 hasConcept C112933361 @default.
- W2897649600 hasConcept C118505674 @default.
- W2897649600 hasConcept C119857082 @default.
- W2897649600 hasConcept C134306372 @default.
- W2897649600 hasConcept C138885662 @default.
- W2897649600 hasConcept C150899416 @default.
- W2897649600 hasConcept C153180895 @default.
- W2897649600 hasConcept C154945302 @default.
- W2897649600 hasConcept C167966045 @default.
- W2897649600 hasConcept C184337299 @default.
- W2897649600 hasConcept C18903297 @default.
- W2897649600 hasConcept C199360897 @default.
- W2897649600 hasConcept C204321447 @default.
- W2897649600 hasConcept C206588197 @default.
- W2897649600 hasConcept C2776401178 @default.
- W2897649600 hasConcept C2781122975 @default.
- W2897649600 hasConcept C33923547 @default.
- W2897649600 hasConcept C36503486 @default.
- W2897649600 hasConcept C39890363 @default.
- W2897649600 hasConcept C41008148 @default.
- W2897649600 hasConcept C41895202 @default.
- W2897649600 hasConcept C49937458 @default.
- W2897649600 hasConcept C81363708 @default.
- W2897649600 hasConcept C86803240 @default.
- W2897649600 hasConcept C98045186 @default.
- W2897649600 hasConceptScore W2897649600C108583219 @default.
- W2897649600 hasConceptScore W2897649600C111919701 @default.
- W2897649600 hasConceptScore W2897649600C112933361 @default.
- W2897649600 hasConceptScore W2897649600C118505674 @default.
- W2897649600 hasConceptScore W2897649600C119857082 @default.
- W2897649600 hasConceptScore W2897649600C134306372 @default.
- W2897649600 hasConceptScore W2897649600C138885662 @default.
- W2897649600 hasConceptScore W2897649600C150899416 @default.
- W2897649600 hasConceptScore W2897649600C153180895 @default.
- W2897649600 hasConceptScore W2897649600C154945302 @default.
- W2897649600 hasConceptScore W2897649600C167966045 @default.
- W2897649600 hasConceptScore W2897649600C184337299 @default.
- W2897649600 hasConceptScore W2897649600C18903297 @default.
- W2897649600 hasConceptScore W2897649600C199360897 @default.
- W2897649600 hasConceptScore W2897649600C204321447 @default.
- W2897649600 hasConceptScore W2897649600C206588197 @default.
- W2897649600 hasConceptScore W2897649600C2776401178 @default.
- W2897649600 hasConceptScore W2897649600C2781122975 @default.
- W2897649600 hasConceptScore W2897649600C33923547 @default.
- W2897649600 hasConceptScore W2897649600C36503486 @default.
- W2897649600 hasConceptScore W2897649600C39890363 @default.
- W2897649600 hasConceptScore W2897649600C41008148 @default.
- W2897649600 hasConceptScore W2897649600C41895202 @default.
- W2897649600 hasConceptScore W2897649600C49937458 @default.
- W2897649600 hasConceptScore W2897649600C81363708 @default.
- W2897649600 hasConceptScore W2897649600C86803240 @default.
- W2897649600 hasConceptScore W2897649600C98045186 @default.
- W2897649600 hasLocation W28976496001 @default.
- W2897649600 hasOpenAccess W2897649600 @default.
- W2897649600 hasPrimaryLocation W28976496001 @default.
- W2897649600 hasRelatedWork W2996856019 @default.
- W2897649600 hasRelatedWork W3018421652 @default.
- W2897649600 hasRelatedWork W3021430260 @default.
- W2897649600 hasRelatedWork W3091976719 @default.
- W2897649600 hasRelatedWork W3192840557 @default.
- W2897649600 hasRelatedWork W4220996320 @default.
- W2897649600 hasRelatedWork W4285149559 @default.
- W2897649600 hasRelatedWork W4312200629 @default.
- W2897649600 hasRelatedWork W4382286161 @default.
- W2897649600 hasRelatedWork W4386213806 @default.
- W2897649600 isParatext "false" @default.
- W2897649600 isRetracted "false" @default.
- W2897649600 magId "2897649600" @default.
- W2897649600 workType "article" @default.