Matches in SemOpenAlex for { <https://semopenalex.org/work/W2790473231> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2790473231 endingPage "93" @default.
- W2790473231 startingPage "82" @default.
- W2790473231 abstract "Abstract This paper presents a novel hyperspectral image (HSI) classification framework by exploiting multi-scale spectral-spatial features via hierarchical recurrent neural networks. The neighborhood information plays an important role in the image classification process. Convolutional neural networks (CNNs) have been shown to be effective in learning the local features of HSI. However, CNNs do not consider the spatial dependency of non-adjacent image patches. Recurrent neural networks (RNNs) can effectively establish the relationship of non-adjacent image patches, but it can only be applied to single-dimensional (1D) sequence. In this paper, we propose multi-scale hierarchical recurrent neural networks (MHRNNs) to learn the spatial dependency of non-adjacent image patches in the two-dimension (2D) spatial domain. First, to better represent the objects with different scales, we generate multi-scale 3D image patches of central pixel and surrounding pixels. Then, 3D CNNs extract the local spectral-spatial feature from each 3D image patch, respectively. Finally, multi-scale 1D sequences in eight directions are constructed on the 3D local feature domain, and MHRNNs are proposed to capture the spatial dependency of local spectral-spatial features at different scales. The proposed method not only considers the local spectral-spatial features of the HSI, but also captures the spatial dependency of non-adjacent image patches at different scales. Experiments are performed on three real HSI datasets. The results demonstrate the superiority of the proposed method over several state-of-the-art methods in both visual appearance and classification accuracy." @default.
- W2790473231 created "2018-03-29" @default.
- W2790473231 creator A5005772506 @default.
- W2790473231 creator A5017377911 @default.
- W2790473231 date "2018-06-01" @default.
- W2790473231 modified "2023-10-16" @default.
- W2790473231 title "Multi-scale hierarchical recurrent neural networks for hyperspectral image classification" @default.
- W2790473231 cites W1512976292 @default.
- W2790473231 cites W1843514792 @default.
- W2790473231 cites W1950365613 @default.
- W2790473231 cites W2018482939 @default.
- W2790473231 cites W2029316659 @default.
- W2790473231 cites W2041100636 @default.
- W2790473231 cites W2077028485 @default.
- W2790473231 cites W2090424610 @default.
- W2790473231 cites W2097915756 @default.
- W2790473231 cites W2103094532 @default.
- W2790473231 cites W2105492591 @default.
- W2790473231 cites W2127199143 @default.
- W2790473231 cites W2144151128 @default.
- W2790473231 cites W2151599207 @default.
- W2790473231 cites W2152057649 @default.
- W2790473231 cites W2166923144 @default.
- W2790473231 cites W2257307118 @default.
- W2790473231 cites W2267317359 @default.
- W2790473231 cites W2314785379 @default.
- W2790473231 cites W2342880667 @default.
- W2790473231 cites W2343108676 @default.
- W2790473231 cites W2500751094 @default.
- W2790473231 cites W2507855991 @default.
- W2790473231 cites W2512351403 @default.
- W2790473231 cites W2519653196 @default.
- W2790473231 cites W2523396434 @default.
- W2790473231 cites W2555840851 @default.
- W2790473231 cites W2557543785 @default.
- W2790473231 cites W2577727229 @default.
- W2790473231 cites W2592737629 @default.
- W2790473231 cites W2744582969 @default.
- W2790473231 cites W2747638294 @default.
- W2790473231 cites W3103856189 @default.
- W2790473231 cites W4240485910 @default.
- W2790473231 doi "https://doi.org/10.1016/j.neucom.2018.03.012" @default.
- W2790473231 hasPublicationYear "2018" @default.
- W2790473231 type Work @default.
- W2790473231 sameAs 2790473231 @default.
- W2790473231 citedByCount "53" @default.
- W2790473231 countsByYear W27904732312018 @default.
- W2790473231 countsByYear W27904732312019 @default.
- W2790473231 countsByYear W27904732312020 @default.
- W2790473231 countsByYear W27904732312021 @default.
- W2790473231 countsByYear W27904732312022 @default.
- W2790473231 countsByYear W27904732312023 @default.
- W2790473231 crossrefType "journal-article" @default.
- W2790473231 hasAuthorship W2790473231A5005772506 @default.
- W2790473231 hasAuthorship W2790473231A5017377911 @default.
- W2790473231 hasConcept C115961682 @default.
- W2790473231 hasConcept C153180895 @default.
- W2790473231 hasConcept C154945302 @default.
- W2790473231 hasConcept C159078339 @default.
- W2790473231 hasConcept C205649164 @default.
- W2790473231 hasConcept C2778755073 @default.
- W2790473231 hasConcept C41008148 @default.
- W2790473231 hasConcept C50644808 @default.
- W2790473231 hasConcept C58640448 @default.
- W2790473231 hasConceptScore W2790473231C115961682 @default.
- W2790473231 hasConceptScore W2790473231C153180895 @default.
- W2790473231 hasConceptScore W2790473231C154945302 @default.
- W2790473231 hasConceptScore W2790473231C159078339 @default.
- W2790473231 hasConceptScore W2790473231C205649164 @default.
- W2790473231 hasConceptScore W2790473231C2778755073 @default.
- W2790473231 hasConceptScore W2790473231C41008148 @default.
- W2790473231 hasConceptScore W2790473231C50644808 @default.
- W2790473231 hasConceptScore W2790473231C58640448 @default.
- W2790473231 hasLocation W27904732311 @default.
- W2790473231 hasOpenAccess W2790473231 @default.
- W2790473231 hasPrimaryLocation W27904732311 @default.
- W2790473231 hasRelatedWork W1869808405 @default.
- W2790473231 hasRelatedWork W2018257962 @default.
- W2790473231 hasRelatedWork W2028628118 @default.
- W2790473231 hasRelatedWork W2031007444 @default.
- W2790473231 hasRelatedWork W2565015337 @default.
- W2790473231 hasRelatedWork W2775464024 @default.
- W2790473231 hasRelatedWork W2783789044 @default.
- W2790473231 hasRelatedWork W2891352623 @default.
- W2790473231 hasRelatedWork W3211035526 @default.
- W2790473231 hasRelatedWork W4291701050 @default.
- W2790473231 hasVolume "294" @default.
- W2790473231 isParatext "false" @default.
- W2790473231 isRetracted "false" @default.
- W2790473231 magId "2790473231" @default.
- W2790473231 workType "article" @default.