FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893766181> ?p ?o ?g. }

• W2893766181 abstract "Deep learning models based on CNNs are predominantly used in image classification tasks. Such approaches, assuming independence of object categories, normally use a CNN as a feature learner and apply a flat classifier on top of it. Object classes in many settings have hierarchical relations, and classifiers exploiting these relations should perform better. We propose hierarchical classification models combining a CNN to extract hierarchical representations of images, and an RNN or sequence-to-sequence model to capture a hierarchical tree of classes. In addition, we apply residual learning to the RNN part in oder to facilitate training our compound model and improve generalization of the model. Experimental results on a real world proprietary dataset of images show that our hierarchical networks perform better than state-of-the-art CNNs." @default.
• W2893766181 created "2018-10-05" @default.
• W2893766181 creator A5013049879 @default.
• W2893766181 creator A5060826513 @default.
• W2893766181 creator A5080783529 @default.
• W2893766181 date "2018-09-25" @default.
• W2893766181 modified "2023-09-22" @default.
• W2893766181 title "Combined convolutional and recurrent neural networks for hierarchical classification of images" @default.
• W2893766181 cites W1686810756 @default.
• W2893766181 cites W1825675169 @default.
• W2893766181 cites W1849277567 @default.
• W2893766181 cites W1851597118 @default.
• W2893766181 cites W1934184906 @default.
• W2893766181 cites W1967542092 @default.
• W2893766181 cites W1967732418 @default.
• W2893766181 cites W1968913370 @default.
• W2893766181 cites W1974907760 @default.
• W2893766181 cites W1979936637 @default.
• W2893766181 cites W2010132303 @default.
• W2893766181 cites W2061851712 @default.
• W2893766181 cites W2102492119 @default.
• W2893766181 cites W2106097867 @default.
• W2893766181 cites W2107215754 @default.
• W2893766181 cites W2114315281 @default.
• W2893766181 cites W2122585011 @default.
• W2893766181 cites W2124678650 @default.
• W2893766181 cites W2127723919 @default.
• W2893766181 cites W2134665698 @default.
• W2893766181 cites W2148141637 @default.
• W2893766181 cites W2157065343 @default.
• W2893766181 cites W2160684493 @default.
• W2893766181 cites W2163605009 @default.
• W2893766181 cites W2194775991 @default.
• W2893766181 cites W2269938945 @default.
• W2893766181 cites W2756815061 @default.
• W2893766181 cites W2772752821 @default.
• W2893766181 cites W2803270043 @default.
• W2893766181 cites W2884585870 @default.
• W2893766181 cites W2962860144 @default.
• W2893766181 cites W2963420686 @default.
• W2893766181 cites W2963513598 @default.
• W2893766181 cites W2963745697 @default.
• W2893766181 cites W607748843 @default.
• W2893766181 hasPublicationYear "2018" @default.
• W2893766181 type Work @default.
• W2893766181 sameAs 2893766181 @default.
• W2893766181 citedByCount "2" @default.
• W2893766181 countsByYear W28937661812021 @default.
• W2893766181 crossrefType "posted-content" @default.
• W2893766181 hasAuthorship W2893766181A5013049879 @default.
• W2893766181 hasAuthorship W2893766181A5060826513 @default.
• W2893766181 hasAuthorship W2893766181A5080783529 @default.
• W2893766181 hasConcept C119857082 @default.
• W2893766181 hasConcept C124101348 @default.
• W2893766181 hasConcept C134306372 @default.
• W2893766181 hasConcept C138885662 @default.
• W2893766181 hasConcept C144986985 @default.
• W2893766181 hasConcept C147168706 @default.
• W2893766181 hasConcept C153180895 @default.
• W2893766181 hasConcept C154945302 @default.
• W2893766181 hasConcept C177148314 @default.
• W2893766181 hasConcept C2776401178 @default.
• W2893766181 hasConcept C2778112365 @default.
• W2893766181 hasConcept C2781238097 @default.
• W2893766181 hasConcept C33923547 @default.
• W2893766181 hasConcept C41008148 @default.
• W2893766181 hasConcept C41895202 @default.
• W2893766181 hasConcept C50644808 @default.
• W2893766181 hasConcept C54355233 @default.
• W2893766181 hasConcept C81363708 @default.
• W2893766181 hasConcept C86803240 @default.
• W2893766181 hasConcept C95623464 @default.
• W2893766181 hasConceptScore W2893766181C119857082 @default.
• W2893766181 hasConceptScore W2893766181C124101348 @default.
• W2893766181 hasConceptScore W2893766181C134306372 @default.
• W2893766181 hasConceptScore W2893766181C138885662 @default.
• W2893766181 hasConceptScore W2893766181C144986985 @default.
• W2893766181 hasConceptScore W2893766181C147168706 @default.
• W2893766181 hasConceptScore W2893766181C153180895 @default.
• W2893766181 hasConceptScore W2893766181C154945302 @default.
• W2893766181 hasConceptScore W2893766181C177148314 @default.
• W2893766181 hasConceptScore W2893766181C2776401178 @default.
• W2893766181 hasConceptScore W2893766181C2778112365 @default.
• W2893766181 hasConceptScore W2893766181C2781238097 @default.
• W2893766181 hasConceptScore W2893766181C33923547 @default.
• W2893766181 hasConceptScore W2893766181C41008148 @default.
• W2893766181 hasConceptScore W2893766181C41895202 @default.
• W2893766181 hasConceptScore W2893766181C50644808 @default.
• W2893766181 hasConceptScore W2893766181C54355233 @default.
• W2893766181 hasConceptScore W2893766181C81363708 @default.
• W2893766181 hasConceptScore W2893766181C86803240 @default.
• W2893766181 hasConceptScore W2893766181C95623464 @default.
• W2893766181 hasOpenAccess W2893766181 @default.
• W2893766181 hasRelatedWork W1937922215 @default.
• W2893766181 hasRelatedWork W2109992539 @default.
• W2893766181 hasRelatedWork W2257307118 @default.
• W2893766181 hasRelatedWork W2551662533 @default.
• W2893766181 hasRelatedWork W2739797317 @default.
• W2893766181 hasRelatedWork W2751746637 @default.
• W2893766181 hasRelatedWork W2772752821 @default.

• next