FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3126963567> ?p ?o ?g. }

• W3126963567 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 known 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 order to facilitate training our compound model and improve generalization of the model. Experimental results on a public and a real world proprietary dataset of images show that our hierarchical networks perform better than state-of-the-art CNNs." @default.
• W3126963567 created "2021-02-15" @default.
• W3126963567 creator A5013049879 @default.
• W3126963567 creator A5060826513 @default.
• W3126963567 creator A5080783529 @default.
• W3126963567 date "2020-12-10" @default.
• W3126963567 modified "2023-10-16" @default.
• W3126963567 title "Combined Convolutional and Recurrent Neural Networks for Hierarchical Classification of Images" @default.
• W3126963567 cites W1849277567 @default.
• W3126963567 cites W1851597118 @default.
• W3126963567 cites W1934184906 @default.
• W3126963567 cites W1967542092 @default.
• W3126963567 cites W1967732418 @default.
• W3126963567 cites W1968913370 @default.
• W3126963567 cites W1974907760 @default.
• W3126963567 cites W1979936637 @default.
• W3126963567 cites W2010132303 @default.
• W3126963567 cites W2061851712 @default.
• W3126963567 cites W2106097867 @default.
• W3126963567 cites W2114315281 @default.
• W3126963567 cites W2122585011 @default.
• W3126963567 cites W2134665698 @default.
• W3126963567 cites W2148141637 @default.
• W3126963567 cites W2157331557 @default.
• W3126963567 cites W2160684493 @default.
• W3126963567 cites W2194775991 @default.
• W3126963567 cites W2269938945 @default.
• W3126963567 cites W2752782242 @default.
• W3126963567 cites W2772752821 @default.
• W3126963567 cites W2884585870 @default.
• W3126963567 cites W2962860144 @default.
• W3126963567 cites W2963513598 @default.
• W3126963567 cites W2963745697 @default.
• W3126963567 cites W607748843 @default.
• W3126963567 doi "https://doi.org/10.1109/bigdata50022.2020.9378237" @default.
• W3126963567 hasPublicationYear "2020" @default.
• W3126963567 type Work @default.
• W3126963567 sameAs 3126963567 @default.
• W3126963567 citedByCount "1" @default.
• W3126963567 countsByYear W31269635672023 @default.
• W3126963567 crossrefType "proceedings-article" @default.
• W3126963567 hasAuthorship W3126963567A5013049879 @default.
• W3126963567 hasAuthorship W3126963567A5060826513 @default.
• W3126963567 hasAuthorship W3126963567A5080783529 @default.
• W3126963567 hasBestOaLocation W31269635672 @default.
• W3126963567 hasConcept C113174947 @default.
• W3126963567 hasConcept C115961682 @default.
• W3126963567 hasConcept C119857082 @default.
• W3126963567 hasConcept C124101348 @default.
• W3126963567 hasConcept C134306372 @default.
• W3126963567 hasConcept C138885662 @default.
• W3126963567 hasConcept C144986985 @default.
• W3126963567 hasConcept C147168706 @default.
• W3126963567 hasConcept C153180895 @default.
• W3126963567 hasConcept C154945302 @default.
• W3126963567 hasConcept C177148314 @default.
• W3126963567 hasConcept C2776401178 @default.
• W3126963567 hasConcept C2778112365 @default.
• W3126963567 hasConcept C2781238097 @default.
• W3126963567 hasConcept C33923547 @default.
• W3126963567 hasConcept C41008148 @default.
• W3126963567 hasConcept C41895202 @default.
• W3126963567 hasConcept C50644808 @default.
• W3126963567 hasConcept C54355233 @default.
• W3126963567 hasConcept C75294576 @default.
• W3126963567 hasConcept C81363708 @default.
• W3126963567 hasConcept C86803240 @default.
• W3126963567 hasConcept C95623464 @default.
• W3126963567 hasConceptScore W3126963567C113174947 @default.
• W3126963567 hasConceptScore W3126963567C115961682 @default.
• W3126963567 hasConceptScore W3126963567C119857082 @default.
• W3126963567 hasConceptScore W3126963567C124101348 @default.
• W3126963567 hasConceptScore W3126963567C134306372 @default.
• W3126963567 hasConceptScore W3126963567C138885662 @default.
• W3126963567 hasConceptScore W3126963567C144986985 @default.
• W3126963567 hasConceptScore W3126963567C147168706 @default.
• W3126963567 hasConceptScore W3126963567C153180895 @default.
• W3126963567 hasConceptScore W3126963567C154945302 @default.
• W3126963567 hasConceptScore W3126963567C177148314 @default.
• W3126963567 hasConceptScore W3126963567C2776401178 @default.
• W3126963567 hasConceptScore W3126963567C2778112365 @default.
• W3126963567 hasConceptScore W3126963567C2781238097 @default.
• W3126963567 hasConceptScore W3126963567C33923547 @default.
• W3126963567 hasConceptScore W3126963567C41008148 @default.
• W3126963567 hasConceptScore W3126963567C41895202 @default.
• W3126963567 hasConceptScore W3126963567C50644808 @default.
• W3126963567 hasConceptScore W3126963567C54355233 @default.
• W3126963567 hasConceptScore W3126963567C75294576 @default.
• W3126963567 hasConceptScore W3126963567C81363708 @default.
• W3126963567 hasConceptScore W3126963567C86803240 @default.
• W3126963567 hasConceptScore W3126963567C95623464 @default.
• W3126963567 hasLocation W31269635671 @default.
• W3126963567 hasLocation W31269635672 @default.
• W3126963567 hasOpenAccess W3126963567 @default.
• W3126963567 hasPrimaryLocation W31269635671 @default.
• W3126963567 hasRelatedWork W2563096758 @default.
• W3126963567 hasRelatedWork W2742991909 @default.
• W3126963567 hasRelatedWork W2767651786 @default.
• W3126963567 hasRelatedWork W2912288872 @default.
• W3126963567 hasRelatedWork W2972035100 @default.

• next