FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894990412> ?p ?o ?g. }

• W2894990412 endingPage "2972" @default.
• W2894990412 startingPage "2963" @default.
• W2894990412 abstract "At present, convolutional neural networks (CNNs) have become popular in visual classification tasks because of their superior performance. However, CNN-based methods do not consider the correlation of visual data to be classified. Recently, graph convolutional networks (GCNs) have mitigated this problem by modeling the pairwise relationship in visual data. Real-world tasks of visual classification typically must address numerous complex relationships in the data, which are not fit for the modeling of the graph structure using GCNs. Therefore, it is vital to explore the underlying correlation of visual data. Regarding this issue, we propose a framework called the hypergraph-induced convolutional network to explore the high-order correlation in visual data during deep neural networks. First, a hypergraph structure is constructed to formulate the relationship in visual data. Then, the high-order correlation is optimized by a learning process based on the constructed hypergraph. The classification tasks are performed by considering the high-order correlation in the data. Thus, the convolution of the hypergraph-induced convolutional network is based on the corresponding high-order relationship, and the optimization on the network uses each data and considers the high-order correlation of the data. To evaluate the proposed hypergraph-induced convolutional network framework, we have conducted experiments on three visual data sets: the National Taiwan University 3-D model data set, Princeton Shape Benchmark, and multiview RGB-depth object data set. The experimental results and comparison in all data sets demonstrate the effectiveness of our proposed hypergraph-induced convolutional network compared with the state-of-the-art methods." @default.
• W2894990412 created "2018-10-12" @default.
• W2894990412 creator A5001543788 @default.
• W2894990412 creator A5024743253 @default.
• W2894990412 creator A5046896679 @default.
• W2894990412 creator A5068911982 @default.
• W2894990412 creator A5073110370 @default.
• W2894990412 creator A5079764771 @default.
• W2894990412 creator A5085211629 @default.
• W2894990412 date "2019-10-01" @default.
• W2894990412 modified "2023-10-11" @default.
• W2894990412 title "Hypergraph-Induced Convolutional Networks for Visual Classification" @default.
• W2894990412 cites W113857012 @default.
• W2894990412 cites W1223058609 @default.
• W2894990412 cites W1644641054 @default.
• W2894990412 cites W1954735160 @default.
• W2894990412 cites W2000738214 @default.
• W2894990412 cites W2021122545 @default.
• W2894990412 cites W2030922352 @default.
• W2894990412 cites W2059272842 @default.
• W2894990412 cites W2068078373 @default.
• W2894990412 cites W2072750214 @default.
• W2894990412 cites W2099789128 @default.
• W2894990412 cites W2115108235 @default.
• W2894990412 cites W2116341502 @default.
• W2894990412 cites W2134557905 @default.
• W2894990412 cites W2216850363 @default.
• W2894990412 cites W2318793210 @default.
• W2894990412 cites W2342709286 @default.
• W2894990412 cites W2358876993 @default.
• W2894990412 cites W2503066070 @default.
• W2894990412 cites W2519210008 @default.
• W2894990412 cites W2519653196 @default.
• W2894990412 cites W2538244214 @default.
• W2894990412 cites W2543732458 @default.
• W2894990412 cites W2559435482 @default.
• W2894990412 cites W2559785631 @default.
• W2894990412 cites W2591638990 @default.
• W2894990412 cites W2605793178 @default.
• W2894990412 cites W2618530766 @default.
• W2894990412 cites W2752880541 @default.
• W2894990412 cites W2773771410 @default.
• W2894990412 cites W2783231089 @default.
• W2894990412 cites W2889055034 @default.
• W2894990412 cites W3122665668 @default.
• W2894990412 cites W816459170 @default.
• W2894990412 doi "https://doi.org/10.1109/tnnls.2018.2869747" @default.
• W2894990412 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30295630" @default.
• W2894990412 hasPublicationYear "2019" @default.
• W2894990412 type Work @default.
• W2894990412 sameAs 2894990412 @default.
• W2894990412 citedByCount "48" @default.
• W2894990412 countsByYear W28949904122019 @default.
• W2894990412 countsByYear W28949904122020 @default.
• W2894990412 countsByYear W28949904122021 @default.
• W2894990412 countsByYear W28949904122022 @default.
• W2894990412 countsByYear W28949904122023 @default.
• W2894990412 crossrefType "journal-article" @default.
• W2894990412 hasAuthorship W2894990412A5001543788 @default.
• W2894990412 hasAuthorship W2894990412A5024743253 @default.
• W2894990412 hasAuthorship W2894990412A5046896679 @default.
• W2894990412 hasAuthorship W2894990412A5068911982 @default.
• W2894990412 hasAuthorship W2894990412A5073110370 @default.
• W2894990412 hasAuthorship W2894990412A5079764771 @default.
• W2894990412 hasAuthorship W2894990412A5085211629 @default.
• W2894990412 hasConcept C117220453 @default.
• W2894990412 hasConcept C118615104 @default.
• W2894990412 hasConcept C124101348 @default.
• W2894990412 hasConcept C132525143 @default.
• W2894990412 hasConcept C13280743 @default.
• W2894990412 hasConcept C153180895 @default.
• W2894990412 hasConcept C154945302 @default.
• W2894990412 hasConcept C177264268 @default.
• W2894990412 hasConcept C184898388 @default.
• W2894990412 hasConcept C185798385 @default.
• W2894990412 hasConcept C199360897 @default.
• W2894990412 hasConcept C205649164 @default.
• W2894990412 hasConcept C2524010 @default.
• W2894990412 hasConcept C2781221856 @default.
• W2894990412 hasConcept C33923547 @default.
• W2894990412 hasConcept C41008148 @default.
• W2894990412 hasConcept C58489278 @default.
• W2894990412 hasConcept C80444323 @default.
• W2894990412 hasConcept C81363708 @default.
• W2894990412 hasConceptScore W2894990412C117220453 @default.
• W2894990412 hasConceptScore W2894990412C118615104 @default.
• W2894990412 hasConceptScore W2894990412C124101348 @default.
• W2894990412 hasConceptScore W2894990412C132525143 @default.
• W2894990412 hasConceptScore W2894990412C13280743 @default.
• W2894990412 hasConceptScore W2894990412C153180895 @default.
• W2894990412 hasConceptScore W2894990412C154945302 @default.
• W2894990412 hasConceptScore W2894990412C177264268 @default.
• W2894990412 hasConceptScore W2894990412C184898388 @default.
• W2894990412 hasConceptScore W2894990412C185798385 @default.
• W2894990412 hasConceptScore W2894990412C199360897 @default.
• W2894990412 hasConceptScore W2894990412C205649164 @default.
• W2894990412 hasConceptScore W2894990412C2524010 @default.
• W2894990412 hasConceptScore W2894990412C2781221856 @default.

• next