Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964076366> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2964076366 endingPage "159" @default.
- W2964076366 startingPage "151" @default.
- W2964076366 abstract "Abstract In this paper, we study the problem of semi-supervised structured output prediction, which aims to learn predictors for structured outputs, such as sequences, tree nodes, vectors, etc., from a set of data points of both input–output pairs and single inputs without outputs. The traditional methods to solve this problem usually learn one single predictor for all the data points, and ignore the variety of the different data points. Different parts of the data set may have different local distributions and require different optimal local predictors. To overcome this disadvantage of existing methods, we propose to learn different local predictors for neighborhoods of different data points, and the missing structured outputs simultaneously. In the neighborhood of each data point, we proposed to learn a linear predictor by minimizing both the complexity of the predictor and the upper bound of the structured prediction loss. The minimization is conducted by gradient descent algorithms. Experiments over four benchmark data sets, including DDSM mammography medical images, SUN natural image data set, Cora research paper data set, and Spanish news wire article sentence data set, show the advantages of the proposed method." @default.
- W2964076366 created "2019-07-30" @default.
- W2964076366 creator A5018243964 @default.
- W2964076366 date "2017-01-01" @default.
- W2964076366 modified "2023-09-24" @default.
- W2964076366 title "Semi-supervised learning of local structured output predictors" @default.
- W2964076366 cites W1065020085 @default.
- W2964076366 cites W1072798930 @default.
- W2964076366 cites W1136224152 @default.
- W2964076366 cites W1141054642 @default.
- W2964076366 cites W1146941609 @default.
- W2964076366 cites W1196375415 @default.
- W2964076366 cites W1211177409 @default.
- W2964076366 cites W125763370 @default.
- W2964076366 cites W1498188640 @default.
- W2964076366 cites W1822128848 @default.
- W2964076366 cites W1932216657 @default.
- W2964076366 cites W1964222026 @default.
- W2964076366 cites W1984058506 @default.
- W2964076366 cites W1986290085 @default.
- W2964076366 cites W1987598996 @default.
- W2964076366 cites W2012150114 @default.
- W2964076366 cites W2017814585 @default.
- W2964076366 cites W2036216970 @default.
- W2964076366 cites W2043385659 @default.
- W2964076366 cites W2063036189 @default.
- W2964076366 cites W2079597242 @default.
- W2964076366 cites W2080058960 @default.
- W2964076366 cites W2091003138 @default.
- W2964076366 cites W2131187138 @default.
- W2964076366 cites W2137450504 @default.
- W2964076366 cites W2141879010 @default.
- W2964076366 cites W2171516886 @default.
- W2964076366 cites W2210294562 @default.
- W2964076366 cites W2217354024 @default.
- W2964076366 cites W2322573259 @default.
- W2964076366 cites W274514816 @default.
- W2964076366 cites W2962785982 @default.
- W2964076366 cites W2963452449 @default.
- W2964076366 cites W52733133 @default.
- W2964076366 cites W759621834 @default.
- W2964076366 cites W766853659 @default.
- W2964076366 cites W835511631 @default.
- W2964076366 cites W839698853 @default.
- W2964076366 cites W934909069 @default.
- W2964076366 cites W601771670 @default.
- W2964076366 doi "https://doi.org/10.1016/j.neucom.2016.02.086" @default.
- W2964076366 hasPublicationYear "2017" @default.
- W2964076366 type Work @default.
- W2964076366 sameAs 2964076366 @default.
- W2964076366 citedByCount "3" @default.
- W2964076366 countsByYear W29640763662018 @default.
- W2964076366 countsByYear W29640763662019 @default.
- W2964076366 countsByYear W29640763662022 @default.
- W2964076366 crossrefType "journal-article" @default.
- W2964076366 hasAuthorship W2964076366A5018243964 @default.
- W2964076366 hasBestOaLocation W29640763662 @default.
- W2964076366 hasConcept C119857082 @default.
- W2964076366 hasConcept C136389625 @default.
- W2964076366 hasConcept C154945302 @default.
- W2964076366 hasConcept C22367795 @default.
- W2964076366 hasConcept C33923547 @default.
- W2964076366 hasConcept C41008148 @default.
- W2964076366 hasConcept C50644808 @default.
- W2964076366 hasConcept C58973888 @default.
- W2964076366 hasConceptScore W2964076366C119857082 @default.
- W2964076366 hasConceptScore W2964076366C136389625 @default.
- W2964076366 hasConceptScore W2964076366C154945302 @default.
- W2964076366 hasConceptScore W2964076366C22367795 @default.
- W2964076366 hasConceptScore W2964076366C33923547 @default.
- W2964076366 hasConceptScore W2964076366C41008148 @default.
- W2964076366 hasConceptScore W2964076366C50644808 @default.
- W2964076366 hasConceptScore W2964076366C58973888 @default.
- W2964076366 hasFunder F4320335787 @default.
- W2964076366 hasLocation W29640763661 @default.
- W2964076366 hasLocation W29640763662 @default.
- W2964076366 hasOpenAccess W2964076366 @default.
- W2964076366 hasPrimaryLocation W29640763661 @default.
- W2964076366 hasRelatedWork W2295628041 @default.
- W2964076366 hasRelatedWork W2752124967 @default.
- W2964076366 hasRelatedWork W2981850339 @default.
- W2964076366 hasRelatedWork W3094076422 @default.
- W2964076366 hasRelatedWork W3095538999 @default.
- W2964076366 hasRelatedWork W3162567751 @default.
- W2964076366 hasRelatedWork W3170950703 @default.
- W2964076366 hasRelatedWork W3210156800 @default.
- W2964076366 hasRelatedWork W4226172683 @default.
- W2964076366 hasRelatedWork W4249546094 @default.
- W2964076366 hasVolume "220" @default.
- W2964076366 isParatext "false" @default.
- W2964076366 isRetracted "false" @default.
- W2964076366 magId "2964076366" @default.
- W2964076366 workType "article" @default.