FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989165718> ?p ?o ?g. }

• W2989165718 endingPage "3633" @default.
• W2989165718 startingPage "3620" @default.
• W2989165718 abstract "Outliers due to occlusion, pixel corruption, and so on pose serious challenges to face recognition despite the recent progress brought by sparse representation. In this article, we show that robust statistics implemented by the state-of-the-art methods are insufficient for robustness against dense gross errors. By modeling the distribution of coding residuals with a Laplacian-uniform mixture, we obtain a sparse representation that is significantly more robust than the previous methods. The nonconvex error term of the implemented objective function is nondifferentiable at zero and cannot be properly addressed by the usual iteratively reweighted least-squares formulation. We show that an iterative robust coding algorithm can be derived by local linear approximation of the nonconvex error term, which is both effective and efficient. With iteratively reweighted l <sub xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sub> minimization of the error term, the proposed algorithm is capable of handling the sparsity assumption of the coding errors more appropriately than the previous methods. Notably, it has the distinct property of addressing error detection and error correction cooperatively in the robust coding process. The proposed method demonstrates significantly improved robustness for face recognition against dense gross errors, either contiguous or discontiguous, as verified by extensive experiments." @default.
• W2989165718 created "2019-11-22" @default.
• W2989165718 creator A5001577023 @default.
• W2989165718 creator A5034213282 @default.
• W2989165718 creator A5059209426 @default.
• W2989165718 creator A5076550599 @default.
• W2989165718 creator A5080483357 @default.
• W2989165718 date "2020-09-01" @default.
• W2989165718 modified "2023-10-14" @default.
• W2989165718 title "Laplacian-Uniform Mixture-Driven Iterative Robust Coding With Applications to Face Recognition Against Dense Errors" @default.
• W2989165718 cites W1513013675 @default.
• W2989165718 cites W1600550542 @default.
• W2989165718 cites W1916406603 @default.
• W2989165718 cites W1950843348 @default.
• W2989165718 cites W1975815261 @default.
• W2989165718 cites W1986931325 @default.
• W2989165718 cites W1989702938 @default.
• W2989165718 cites W1996726072 @default.
• W2989165718 cites W2017155271 @default.
• W2989165718 cites W2025217965 @default.
• W2989165718 cites W2050834445 @default.
• W2989165718 cites W2050849575 @default.
• W2989165718 cites W2073940236 @default.
• W2989165718 cites W2076094332 @default.
• W2989165718 cites W2081477191 @default.
• W2989165718 cites W2096204758 @default.
• W2989165718 cites W2098017479 @default.
• W2989165718 cites W2099474347 @default.
• W2989165718 cites W2100556411 @default.
• W2989165718 cites W2101149304 @default.
• W2989165718 cites W2107369107 @default.
• W2989165718 cites W2107861471 @default.
• W2989165718 cites W2115706991 @default.
• W2989165718 cites W2117553576 @default.
• W2989165718 cites W2121647436 @default.
• W2989165718 cites W2123921160 @default.
• W2989165718 cites W2125874614 @default.
• W2989165718 cites W2127031212 @default.
• W2989165718 cites W2129812935 @default.
• W2989165718 cites W2135046866 @default.
• W2989165718 cites W2135160607 @default.
• W2989165718 cites W2136922672 @default.
• W2989165718 cites W2137823674 @default.
• W2989165718 cites W2138451337 @default.
• W2989165718 cites W2143642807 @default.
• W2989165718 cites W2145287260 @default.
• W2989165718 cites W2154332973 @default.
• W2989165718 cites W2157285372 @default.
• W2989165718 cites W2163808566 @default.
• W2989165718 cites W2163922914 @default.
• W2989165718 cites W2164294799 @default.
• W2989165718 cites W2165731615 @default.
• W2989165718 cites W2168602559 @default.
• W2989165718 cites W2325939864 @default.
• W2989165718 cites W2342709286 @default.
• W2989165718 cites W2474352580 @default.
• W2989165718 cites W2514070903 @default.
• W2989165718 cites W2520742745 @default.
• W2989165718 cites W2585551302 @default.
• W2989165718 cites W2607764799 @default.
• W2989165718 cites W2728364730 @default.
• W2989165718 cites W2756807093 @default.
• W2989165718 cites W2790299973 @default.
• W2989165718 cites W2805747803 @default.
• W2989165718 cites W2949483514 @default.
• W2989165718 cites W2963460857 @default.
• W2989165718 cites W2963689635 @default.
• W2989165718 cites W2963958000 @default.
• W2989165718 cites W3022380717 @default.
• W2989165718 cites W3097096317 @default.
• W2989165718 cites W3100830527 @default.
• W2989165718 cites W3102431071 @default.
• W2989165718 cites W3122534566 @default.
• W2989165718 cites W4205806204 @default.
• W2989165718 doi "https://doi.org/10.1109/tnnls.2019.2945372" @default.
• W2989165718 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31714242" @default.
• W2989165718 hasPublicationYear "2020" @default.
• W2989165718 type Work @default.
• W2989165718 sameAs 2989165718 @default.
• W2989165718 citedByCount "2" @default.
• W2989165718 countsByYear W29891657182022 @default.
• W2989165718 countsByYear W29891657182023 @default.
• W2989165718 crossrefType "journal-article" @default.
• W2989165718 hasAuthorship W2989165718A5001577023 @default.
• W2989165718 hasAuthorship W2989165718A5034213282 @default.
• W2989165718 hasAuthorship W2989165718A5059209426 @default.
• W2989165718 hasAuthorship W2989165718A5076550599 @default.
• W2989165718 hasAuthorship W2989165718A5080483357 @default.
• W2989165718 hasConcept C104317684 @default.
• W2989165718 hasConcept C105795698 @default.
• W2989165718 hasConcept C11413529 @default.
• W2989165718 hasConcept C126090379 @default.
• W2989165718 hasConcept C126255220 @default.
• W2989165718 hasConcept C147764199 @default.
• W2989165718 hasConcept C153180895 @default.
• W2989165718 hasConcept C154945302 @default.
• W2989165718 hasConcept C159694833 @default.
• W2989165718 hasConcept C167928553 @default.

• next