FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2257307118> ?p ?o ?g. }

• W2257307118 endingPage "2996" @default.
• W2257307118 startingPage "2983" @default.
• W2257307118 abstract "Deep convolutional neural networks (CNNs) have shown their great success on image classification. CNNs mainly consist of convolutional and pooling layers, both of which are performed on local image areas without considering the dependence among different image regions. However, such dependence is very important for generating explicit image representation. In contrast, recurrent neural networks (RNNs) are well known for their ability of encoding contextual information in sequential data, and they only require a limited number of network parameters. Thus, we proposed the hierarchical RNNs (HRNNs) to encode the contextual dependence in image representation. In HRNNs, each RNN layer focuses on modeling spatial dependence among image regions from the same scale but different locations. While the cross RNN scale connections target on modeling scale dependencies among regions from the same location but different scales. Specifically, we propose two RNN models: 1) hierarchical simple recurrent network (HSRN), which is fast and has low computational cost and 2) hierarchical long-short term memory recurrent network, which performs better than HSRN with the price of higher computational cost. In this paper, we integrate CNNs with HRNNs, and develop end-to-end convolutional hierarchical RNNs (C-HRNNs) for image classification. C-HRNNs not only utilize the discriminative representation power of CNNs, but also utilize the contextual dependence learning ability of our HRNNs. On four of the most challenging object/scene image classification benchmarks, our C-HRNNs achieve the state-of-the-art results on Places 205, SUN 397, and MIT indoor, and the competitive results on ILSVRC 2012." @default.
• W2257307118 created "2016-06-24" @default.
• W2257307118 creator A5006662591 @default.
• W2257307118 creator A5027034650 @default.
• W2257307118 creator A5030921116 @default.
• W2257307118 creator A5036011098 @default.
• W2257307118 creator A5040040696 @default.
• W2257307118 creator A5048015379 @default.
• W2257307118 creator A5076409244 @default.
• W2257307118 date "2016-07-01" @default.
• W2257307118 modified "2023-10-16" @default.
• W2257307118 title "Learning Contextual Dependence With Convolutional Hierarchical Recurrent Neural Networks" @default.
• W2257307118 cites W18669060 @default.
• W2257307118 cites W1922658220 @default.
• W2257307118 cites W1966385142 @default.
• W2257307118 cites W1998808035 @default.
• W2257307118 cites W2006904655 @default.
• W2257307118 cites W2017814585 @default.
• W2257307118 cites W2027922120 @default.
• W2257307118 cites W2033832873 @default.
• W2257307118 cites W2049538695 @default.
• W2257307118 cites W2064675550 @default.
• W2257307118 cites W2070792803 @default.
• W2257307118 cites W2075830955 @default.
• W2257307118 cites W2100495367 @default.
• W2257307118 cites W2102605133 @default.
• W2257307118 cites W2107698128 @default.
• W2257307118 cites W2113325037 @default.
• W2257307118 cites W2130325614 @default.
• W2257307118 cites W2136922672 @default.
• W2257307118 cites W2145287260 @default.
• W2257307118 cites W2151103935 @default.
• W2257307118 cites W2152161678 @default.
• W2257307118 cites W2155893237 @default.
• W2257307118 cites W2157785665 @default.
• W2257307118 cites W2161381512 @default.
• W2257307118 cites W2161969291 @default.
• W2257307118 cites W2166694921 @default.
• W2257307118 cites W2251849926 @default.
• W2257307118 cites W2919115771 @default.
• W2257307118 cites W2951183276 @default.
• W2257307118 cites W2963173190 @default.
• W2257307118 cites W4254816979 @default.
• W2257307118 doi "https://doi.org/10.1109/tip.2016.2548241" @default.
• W2257307118 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/28113173" @default.
• W2257307118 hasPublicationYear "2016" @default.
• W2257307118 type Work @default.
• W2257307118 sameAs 2257307118 @default.
• W2257307118 citedByCount "83" @default.
• W2257307118 countsByYear W22573071182015 @default.
• W2257307118 countsByYear W22573071182016 @default.
• W2257307118 countsByYear W22573071182017 @default.
• W2257307118 countsByYear W22573071182018 @default.
• W2257307118 countsByYear W22573071182019 @default.
• W2257307118 countsByYear W22573071182020 @default.
• W2257307118 countsByYear W22573071182021 @default.
• W2257307118 countsByYear W22573071182022 @default.
• W2257307118 crossrefType "journal-article" @default.
• W2257307118 hasAuthorship W2257307118A5006662591 @default.
• W2257307118 hasAuthorship W2257307118A5027034650 @default.
• W2257307118 hasAuthorship W2257307118A5030921116 @default.
• W2257307118 hasAuthorship W2257307118A5036011098 @default.
• W2257307118 hasAuthorship W2257307118A5040040696 @default.
• W2257307118 hasAuthorship W2257307118A5048015379 @default.
• W2257307118 hasAuthorship W2257307118A5076409244 @default.
• W2257307118 hasBestOaLocation W22573071182 @default.
• W2257307118 hasConcept C115961682 @default.
• W2257307118 hasConcept C119857082 @default.
• W2257307118 hasConcept C147168706 @default.
• W2257307118 hasConcept C153180895 @default.
• W2257307118 hasConcept C154945302 @default.
• W2257307118 hasConcept C17744445 @default.
• W2257307118 hasConcept C199539241 @default.
• W2257307118 hasConcept C2776359362 @default.
• W2257307118 hasConcept C41008148 @default.
• W2257307118 hasConcept C50644808 @default.
• W2257307118 hasConcept C59404180 @default.
• W2257307118 hasConcept C70437156 @default.
• W2257307118 hasConcept C75294576 @default.
• W2257307118 hasConcept C81363708 @default.
• W2257307118 hasConcept C94625758 @default.
• W2257307118 hasConcept C97931131 @default.
• W2257307118 hasConceptScore W2257307118C115961682 @default.
• W2257307118 hasConceptScore W2257307118C119857082 @default.
• W2257307118 hasConceptScore W2257307118C147168706 @default.
• W2257307118 hasConceptScore W2257307118C153180895 @default.
• W2257307118 hasConceptScore W2257307118C154945302 @default.
• W2257307118 hasConceptScore W2257307118C17744445 @default.
• W2257307118 hasConceptScore W2257307118C199539241 @default.
• W2257307118 hasConceptScore W2257307118C2776359362 @default.
• W2257307118 hasConceptScore W2257307118C41008148 @default.
• W2257307118 hasConceptScore W2257307118C50644808 @default.
• W2257307118 hasConceptScore W2257307118C59404180 @default.
• W2257307118 hasConceptScore W2257307118C70437156 @default.
• W2257307118 hasConceptScore W2257307118C75294576 @default.
• W2257307118 hasConceptScore W2257307118C81363708 @default.
• W2257307118 hasConceptScore W2257307118C94625758 @default.
• W2257307118 hasConceptScore W2257307118C97931131 @default.

• next