Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225293721> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4225293721 abstract "Missing data imputation aims to accurately impute the unobserved regions with complete data in real world. Although many recent methods have made remarkable advances, the local homogenous regions especially in boundary and the reasonable of the imputed data are still two most challenging issues. To address these issues, we propose a novel Global to Local Guiding Network (G2LGN) based on generative adversarial network for missing data imputation, which is composed of a Global-Impute-Net (GIN), a Local-Impute-Net (LIN) and an Impute Guider Model (IGM). The GIN looks at the entire missing regions to generate and impute data as a whole. Considering the reasonable of the GIN results, IGM is assigned to capture coherent information between global and local and guide the LIN to look only at a small area centered at the missing focused regions. After the processing of these three modules, local imputed results are concatenated to global imputed results, which impute reasonable values and refine local details from rough to accurate. The comprehensive experiments on both numeric datasets and image dataset demonstrate our method is significantly superior to other 3 state-of-the-art approaches and 7 traditional methods. Besides, the extensive ablation study validates the superior performance for dealing with missing data imputation." @default.
- W4225293721 created "2022-05-05" @default.
- W4225293721 creator A5044367029 @default.
- W4225293721 creator A5046597133 @default.
- W4225293721 creator A5085900553 @default.
- W4225293721 date "2022-05-23" @default.
- W4225293721 modified "2023-09-23" @default.
- W4225293721 title "A Global to Local Guiding Network for Missing Data Imputation" @default.
- W4225293721 cites W1600744878 @default.
- W4225293721 cites W1615057313 @default.
- W4225293721 cites W2019126302 @default.
- W4225293721 cites W2064186732 @default.
- W4225293721 cites W2102148524 @default.
- W4225293721 cites W2134843796 @default.
- W4225293721 cites W2146332392 @default.
- W4225293721 cites W2296244148 @default.
- W4225293721 cites W2886527657 @default.
- W4225293721 cites W2962932373 @default.
- W4225293721 cites W2963077125 @default.
- W4225293721 cites W2966017932 @default.
- W4225293721 cites W3034291999 @default.
- W4225293721 cites W3034431451 @default.
- W4225293721 cites W3034513922 @default.
- W4225293721 cites W3035204081 @default.
- W4225293721 cites W3166340478 @default.
- W4225293721 doi "https://doi.org/10.1109/icassp43922.2022.9746136" @default.
- W4225293721 hasPublicationYear "2022" @default.
- W4225293721 type Work @default.
- W4225293721 citedByCount "0" @default.
- W4225293721 crossrefType "proceedings-article" @default.
- W4225293721 hasAuthorship W4225293721A5044367029 @default.
- W4225293721 hasAuthorship W4225293721A5046597133 @default.
- W4225293721 hasAuthorship W4225293721A5085900553 @default.
- W4225293721 hasConcept C108583219 @default.
- W4225293721 hasConcept C119857082 @default.
- W4225293721 hasConcept C124101348 @default.
- W4225293721 hasConcept C154945302 @default.
- W4225293721 hasConcept C2988773926 @default.
- W4225293721 hasConcept C41008148 @default.
- W4225293721 hasConcept C58041806 @default.
- W4225293721 hasConcept C9357733 @default.
- W4225293721 hasConceptScore W4225293721C108583219 @default.
- W4225293721 hasConceptScore W4225293721C119857082 @default.
- W4225293721 hasConceptScore W4225293721C124101348 @default.
- W4225293721 hasConceptScore W4225293721C154945302 @default.
- W4225293721 hasConceptScore W4225293721C2988773926 @default.
- W4225293721 hasConceptScore W4225293721C41008148 @default.
- W4225293721 hasConceptScore W4225293721C58041806 @default.
- W4225293721 hasConceptScore W4225293721C9357733 @default.
- W4225293721 hasLocation W42252937211 @default.
- W4225293721 hasOpenAccess W4225293721 @default.
- W4225293721 hasPrimaryLocation W42252937211 @default.
- W4225293721 hasRelatedWork W14551267 @default.
- W4225293721 hasRelatedWork W14899464 @default.
- W4225293721 hasRelatedWork W1575975 @default.
- W4225293721 hasRelatedWork W3151196 @default.
- W4225293721 hasRelatedWork W378070 @default.
- W4225293721 hasRelatedWork W3862333 @default.
- W4225293721 hasRelatedWork W5875386 @default.
- W4225293721 hasRelatedWork W6263585 @default.
- W4225293721 hasRelatedWork W7075034 @default.
- W4225293721 hasRelatedWork W961884 @default.
- W4225293721 isParatext "false" @default.
- W4225293721 isRetracted "false" @default.
- W4225293721 workType "article" @default.