Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385757761> ?p ?o ?g. }
- W4385757761 endingPage "16" @default.
- W4385757761 startingPage "1" @default.
- W4385757761 abstract "Hyperspectral unmixing is a crucial task in hyperspectral image processing and analysis. It aims to decompose mixed pixels into pure spectral signatures and their associated abundances. However, most current unmixing methods ignore the reality that the same pixel of a hyperspectral image has many different reflections simultaneously. To address this issue, we propose a multi-task autoencoding model for multiple reflections, which can improve the algorithm’s robustness in complex environments. Our proposed framework uses 3D-CNN-based networks to jointly learn spectral-spatial priors and adapt to different pixels by complementing the advantages of other unmixing methods. The proposed method can quantitatively evaluate each area of data, which helps improve the algorithm’s interpretability. This paper presents MAHUM (Multi-tasks Autoencoder Hyperspectral Unmixing Model), which stacks multiple models to deal with various reflections of complex terrain. We also perform sensitivity analysis on some parameters and show experimental results demonstrating our method’s ability to express the adaptability of different materials in different methods quantitatively." @default.
- W4385757761 created "2023-08-12" @default.
- W4385757761 creator A5006623289 @default.
- W4385757761 creator A5010242765 @default.
- W4385757761 creator A5036283525 @default.
- W4385757761 date "2023-01-01" @default.
- W4385757761 modified "2023-09-26" @default.
- W4385757761 title "MAHUM: a Multi-tasks Autoencoder Hyperspectral Unmixing Model" @default.
- W4385757761 cites W1902016676 @default.
- W4385757761 cites W2019149505 @default.
- W4385757761 cites W2032944446 @default.
- W4385757761 cites W2042626896 @default.
- W4385757761 cites W2051358843 @default.
- W4385757761 cites W2094596373 @default.
- W4385757761 cites W2101837437 @default.
- W4385757761 cites W2114486983 @default.
- W4385757761 cites W2127062304 @default.
- W4385757761 cites W2141494774 @default.
- W4385757761 cites W2142786738 @default.
- W4385757761 cites W2143500192 @default.
- W4385757761 cites W2157321686 @default.
- W4385757761 cites W2161865324 @default.
- W4385757761 cites W2163886442 @default.
- W4385757761 cites W2169924573 @default.
- W4385757761 cites W2527329788 @default.
- W4385757761 cites W2765455392 @default.
- W4385757761 cites W2768479014 @default.
- W4385757761 cites W2774528199 @default.
- W4385757761 cites W2809306703 @default.
- W4385757761 cites W2893348249 @default.
- W4385757761 cites W2894115892 @default.
- W4385757761 cites W2911419410 @default.
- W4385757761 cites W2921511952 @default.
- W4385757761 cites W2932657337 @default.
- W4385757761 cites W2935130647 @default.
- W4385757761 cites W3028000844 @default.
- W4385757761 cites W3035015656 @default.
- W4385757761 cites W3041330594 @default.
- W4385757761 cites W3101195009 @default.
- W4385757761 cites W3110749113 @default.
- W4385757761 cites W3131601043 @default.
- W4385757761 cites W3161263451 @default.
- W4385757761 cites W3168931281 @default.
- W4385757761 cites W3204957802 @default.
- W4385757761 cites W4205095826 @default.
- W4385757761 cites W4206690402 @default.
- W4385757761 cites W4212955958 @default.
- W4385757761 cites W4233760599 @default.
- W4385757761 cites W4285171615 @default.
- W4385757761 cites W4306399448 @default.
- W4385757761 cites W4313438466 @default.
- W4385757761 cites W4366150256 @default.
- W4385757761 cites W4366310757 @default.
- W4385757761 cites W4376481071 @default.
- W4385757761 cites W4380478936 @default.
- W4385757761 doi "https://doi.org/10.1109/tgrs.2023.3304484" @default.
- W4385757761 hasPublicationYear "2023" @default.
- W4385757761 type Work @default.
- W4385757761 citedByCount "0" @default.
- W4385757761 crossrefType "journal-article" @default.
- W4385757761 hasAuthorship W4385757761A5006623289 @default.
- W4385757761 hasAuthorship W4385757761A5010242765 @default.
- W4385757761 hasAuthorship W4385757761A5036283525 @default.
- W4385757761 hasConcept C101738243 @default.
- W4385757761 hasConcept C104317684 @default.
- W4385757761 hasConcept C107673813 @default.
- W4385757761 hasConcept C108583219 @default.
- W4385757761 hasConcept C127313418 @default.
- W4385757761 hasConcept C153180895 @default.
- W4385757761 hasConcept C154945302 @default.
- W4385757761 hasConcept C159078339 @default.
- W4385757761 hasConcept C160633673 @default.
- W4385757761 hasConcept C177606310 @default.
- W4385757761 hasConcept C177769412 @default.
- W4385757761 hasConcept C185592680 @default.
- W4385757761 hasConcept C18903297 @default.
- W4385757761 hasConcept C2781067378 @default.
- W4385757761 hasConcept C31972630 @default.
- W4385757761 hasConcept C41008148 @default.
- W4385757761 hasConcept C55493867 @default.
- W4385757761 hasConcept C62649853 @default.
- W4385757761 hasConcept C63479239 @default.
- W4385757761 hasConcept C86803240 @default.
- W4385757761 hasConceptScore W4385757761C101738243 @default.
- W4385757761 hasConceptScore W4385757761C104317684 @default.
- W4385757761 hasConceptScore W4385757761C107673813 @default.
- W4385757761 hasConceptScore W4385757761C108583219 @default.
- W4385757761 hasConceptScore W4385757761C127313418 @default.
- W4385757761 hasConceptScore W4385757761C153180895 @default.
- W4385757761 hasConceptScore W4385757761C154945302 @default.
- W4385757761 hasConceptScore W4385757761C159078339 @default.
- W4385757761 hasConceptScore W4385757761C160633673 @default.
- W4385757761 hasConceptScore W4385757761C177606310 @default.
- W4385757761 hasConceptScore W4385757761C177769412 @default.
- W4385757761 hasConceptScore W4385757761C185592680 @default.
- W4385757761 hasConceptScore W4385757761C18903297 @default.
- W4385757761 hasConceptScore W4385757761C2781067378 @default.
- W4385757761 hasConceptScore W4385757761C31972630 @default.