FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293812006> ?p ?o ?g. }

• W4293812006 endingPage "13" @default.
• W4293812006 startingPage "1" @default.
• W4293812006 abstract "Unsupervised band selection aims to select informative spectral bands to preprocess hyperspectral images (HSIs) without using labels. Traditional band selection methods only work well on Euclidean data, but ignore structural information of pixels and spectral bands. Moreover, they treat each HSI as a whole to exploit latent spatial information while ignoring the difference of spatial distribution between diverse homogeneous regions. In this paper, we propose a robust dual graph self-representation (RDGSR) method for unsupervised band selection. RDGSR uses superpixel segmentation technique to generate homogenous regions of each HSI to extract spatial information. Based on the segmentation result, the superpixel-based similarity graph and band-based similarity graph are constructed from HSIs to record spatial and structural information. With this knowledge, the dual graph convolution is developed and the <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>l</i> <sub xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2,1</sub> -norm is introduced in the loss function and regularization term to eliminate the noise in rows for robust and effective band selection. The novelty of RDGSR is the joint utilization of the geometric structure of pixels with spatial consistency and the geometric structure of spectral bands to enhance the performance of band selection in a robust <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>l</i> <sub xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2,1</sub> -norm manner. An iterative optimization algorithm is designed to solve the proposed formulation. Substantial experiments on HSI datasets are conducted to verify the superiority of the proposed RDGSR over the state-of-the-art methods. The source code is available at https://github.com/ZhangYongshan/RDGSR." @default.
• W4293812006 created "2022-08-31" @default.
• W4293812006 creator A5009595085 @default.
• W4293812006 creator A5032315273 @default.
• W4293812006 creator A5055814385 @default.
• W4293812006 creator A5078539725 @default.
• W4293812006 date "2022-01-01" @default.
• W4293812006 modified "2023-10-16" @default.
• W4293812006 title "Robust Dual Graph Self-Representation for Unsupervised Hyperspectral Band Selection" @default.
• W4293812006 cites W1501856433 @default.
• W4293812006 cites W1932531222 @default.
• W4293812006 cites W1995295300 @default.
• W4293812006 cites W2047029347 @default.
• W4293812006 cites W2072187267 @default.
• W4293812006 cites W2083666679 @default.
• W4293812006 cites W2135431554 @default.
• W4293812006 cites W2140991832 @default.
• W4293812006 cites W2150120952 @default.
• W4293812006 cites W2150990614 @default.
• W4293812006 cites W2162698522 @default.
• W4293812006 cites W2292865806 @default.
• W4293812006 cites W2340318445 @default.
• W4293812006 cites W2412588858 @default.
• W4293812006 cites W2518815253 @default.
• W4293812006 cites W2571192787 @default.
• W4293812006 cites W2747189523 @default.
• W4293812006 cites W2749577643 @default.
• W4293812006 cites W2751810713 @default.
• W4293812006 cites W2790404832 @default.
• W4293812006 cites W2793357412 @default.
• W4293812006 cites W2793733641 @default.
• W4293812006 cites W2890022946 @default.
• W4293812006 cites W2897121118 @default.
• W4293812006 cites W2913960921 @default.
• W4293812006 cites W2962946486 @default.
• W4293812006 cites W2969940899 @default.
• W4293812006 cites W2979744929 @default.
• W4293812006 cites W2980054274 @default.
• W4293812006 cites W3000675402 @default.
• W4293812006 cites W3001656420 @default.
• W4293812006 cites W3008789903 @default.
• W4293812006 cites W3008911924 @default.
• W4293812006 cites W3023065102 @default.
• W4293812006 cites W3028306149 @default.
• W4293812006 cites W3039321110 @default.
• W4293812006 cites W3046819794 @default.
• W4293812006 cites W3047358975 @default.
• W4293812006 cites W3049737467 @default.
• W4293812006 cites W3080724268 @default.
• W4293812006 cites W3100499011 @default.
• W4293812006 cites W3105100264 @default.
• W4293812006 cites W3108083086 @default.
• W4293812006 cites W3129293716 @default.
• W4293812006 cites W3132576058 @default.
• W4293812006 cites W3133533225 @default.
• W4293812006 cites W3161700323 @default.
• W4293812006 cites W3195258402 @default.
• W4293812006 cites W3197705459 @default.
• W4293812006 cites W3211243520 @default.
• W4293812006 doi "https://doi.org/10.1109/tgrs.2022.3203207" @default.
• W4293812006 hasPublicationYear "2022" @default.
• W4293812006 type Work @default.
• W4293812006 citedByCount "2" @default.
• W4293812006 countsByYear W42938120062023 @default.
• W4293812006 crossrefType "journal-article" @default.
• W4293812006 hasAuthorship W4293812006A5009595085 @default.
• W4293812006 hasAuthorship W4293812006A5032315273 @default.
• W4293812006 hasAuthorship W4293812006A5055814385 @default.
• W4293812006 hasAuthorship W4293812006A5078539725 @default.
• W4293812006 hasConcept C132525143 @default.
• W4293812006 hasConcept C153180895 @default.
• W4293812006 hasConcept C154945302 @default.
• W4293812006 hasConcept C159078339 @default.
• W4293812006 hasConcept C160633673 @default.
• W4293812006 hasConcept C33923547 @default.
• W4293812006 hasConcept C41008148 @default.
• W4293812006 hasConcept C80444323 @default.
• W4293812006 hasConceptScore W4293812006C132525143 @default.
• W4293812006 hasConceptScore W4293812006C153180895 @default.
• W4293812006 hasConceptScore W4293812006C154945302 @default.
• W4293812006 hasConceptScore W4293812006C159078339 @default.
• W4293812006 hasConceptScore W4293812006C160633673 @default.
• W4293812006 hasConceptScore W4293812006C33923547 @default.
• W4293812006 hasConceptScore W4293812006C41008148 @default.
• W4293812006 hasConceptScore W4293812006C80444323 @default.
• W4293812006 hasFunder F4320321001 @default.
• W4293812006 hasFunder F4320322841 @default.
• W4293812006 hasLocation W42938120061 @default.
• W4293812006 hasOpenAccess W4293812006 @default.
• W4293812006 hasPrimaryLocation W42938120061 @default.
• W4293812006 hasRelatedWork W1869808405 @default.
• W4293812006 hasRelatedWork W2018257962 @default.
• W4293812006 hasRelatedWork W2028628118 @default.
• W4293812006 hasRelatedWork W2031007444 @default.
• W4293812006 hasRelatedWork W2136485282 @default.
• W4293812006 hasRelatedWork W2546645752 @default.
• W4293812006 hasRelatedWork W2565015337 @default.
• W4293812006 hasRelatedWork W3034655717 @default.

• next