Matches in SemOpenAlex for { <https://semopenalex.org/work/W2793856863> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2793856863 abstract "Context plays an important role in visual pattern recognition as it provides complementary clues for different learning tasks including image classification and annotation. In the particular scenario of kernel learning, the general recipe of context-based kernel design consists in learning positive semi-definite similarity functions that return high values not only when data share similar content but also similar context. However, in spite of having a positive impact on performance, the use of context in these kernel design methods has not been fully explored; indeed, context has been handcrafted instead of being learned. In this paper, we introduce a novel context-aware kernel design framework based on deep learning. Our method discriminatively learns spatial geometric context as the weights of a deep network (DN). The architecture of this network is fully determined by the solution of an objective function that mixes content, context and regularization, while the parameters of this network determine the most relevant (discriminant) parts of the learned context. We apply this context and kernel learning framework to image classification using the challenging ImageCLEF Photo Annotation benchmark; the latter shows that our deep context learning provides highly effective kernels for image classification as corroborated through extensive experiments." @default.
- W2793856863 created "2018-03-29" @default.
- W2793856863 creator A5017257056 @default.
- W2793856863 creator A5029896607 @default.
- W2793856863 date "2018-03-23" @default.
- W2793856863 modified "2023-09-25" @default.
- W2793856863 title "Learning Deep Context-Network Architectures for Image Annotation" @default.
- W2793856863 cites W1510073064 @default.
- W2793856863 cites W1601437336 @default.
- W2793856863 cites W1877469910 @default.
- W2793856863 cites W2031823405 @default.
- W2793856863 cites W2054103873 @default.
- W2793856863 cites W2069797086 @default.
- W2793856863 cites W2137471889 @default.
- W2793856863 cites W2146024151 @default.
- W2793856863 cites W2155867588 @default.
- W2793856863 cites W2294422256 @default.
- W2793856863 cites W2536305071 @default.
- W2793856863 doi "https://doi.org/10.48550/arxiv.1803.08794" @default.
- W2793856863 hasPublicationYear "2018" @default.
- W2793856863 type Work @default.
- W2793856863 sameAs 2793856863 @default.
- W2793856863 citedByCount "0" @default.
- W2793856863 crossrefType "posted-content" @default.
- W2793856863 hasAuthorship W2793856863A5017257056 @default.
- W2793856863 hasAuthorship W2793856863A5029896607 @default.
- W2793856863 hasBestOaLocation W27938568631 @default.
- W2793856863 hasConcept C103278499 @default.
- W2793856863 hasConcept C108583219 @default.
- W2793856863 hasConcept C114614502 @default.
- W2793856863 hasConcept C115961682 @default.
- W2793856863 hasConcept C119857082 @default.
- W2793856863 hasConcept C122280245 @default.
- W2793856863 hasConcept C12267149 @default.
- W2793856863 hasConcept C13280743 @default.
- W2793856863 hasConcept C151730666 @default.
- W2793856863 hasConcept C153180895 @default.
- W2793856863 hasConcept C154945302 @default.
- W2793856863 hasConcept C185798385 @default.
- W2793856863 hasConcept C205649164 @default.
- W2793856863 hasConcept C2776321320 @default.
- W2793856863 hasConcept C2779343474 @default.
- W2793856863 hasConcept C33923547 @default.
- W2793856863 hasConcept C41008148 @default.
- W2793856863 hasConcept C74193536 @default.
- W2793856863 hasConcept C86803240 @default.
- W2793856863 hasConceptScore W2793856863C103278499 @default.
- W2793856863 hasConceptScore W2793856863C108583219 @default.
- W2793856863 hasConceptScore W2793856863C114614502 @default.
- W2793856863 hasConceptScore W2793856863C115961682 @default.
- W2793856863 hasConceptScore W2793856863C119857082 @default.
- W2793856863 hasConceptScore W2793856863C122280245 @default.
- W2793856863 hasConceptScore W2793856863C12267149 @default.
- W2793856863 hasConceptScore W2793856863C13280743 @default.
- W2793856863 hasConceptScore W2793856863C151730666 @default.
- W2793856863 hasConceptScore W2793856863C153180895 @default.
- W2793856863 hasConceptScore W2793856863C154945302 @default.
- W2793856863 hasConceptScore W2793856863C185798385 @default.
- W2793856863 hasConceptScore W2793856863C205649164 @default.
- W2793856863 hasConceptScore W2793856863C2776321320 @default.
- W2793856863 hasConceptScore W2793856863C2779343474 @default.
- W2793856863 hasConceptScore W2793856863C33923547 @default.
- W2793856863 hasConceptScore W2793856863C41008148 @default.
- W2793856863 hasConceptScore W2793856863C74193536 @default.
- W2793856863 hasConceptScore W2793856863C86803240 @default.
- W2793856863 hasLocation W27938568631 @default.
- W2793856863 hasOpenAccess W2793856863 @default.
- W2793856863 hasPrimaryLocation W27938568631 @default.
- W2793856863 hasRelatedWork W2049539567 @default.
- W2793856863 hasRelatedWork W2103444992 @default.
- W2793856863 hasRelatedWork W2110459882 @default.
- W2793856863 hasRelatedWork W2141018987 @default.
- W2793856863 hasRelatedWork W2585586666 @default.
- W2793856863 hasRelatedWork W2603933437 @default.
- W2793856863 hasRelatedWork W2900794075 @default.
- W2793856863 hasRelatedWork W2947809439 @default.
- W2793856863 hasRelatedWork W3136979370 @default.
- W2793856863 hasRelatedWork W3153922349 @default.
- W2793856863 isParatext "false" @default.
- W2793856863 isRetracted "false" @default.
- W2793856863 magId "2793856863" @default.
- W2793856863 workType "article" @default.