Matches in SemOpenAlex for { <https://semopenalex.org/work/W2022203019> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2022203019 endingPage "1799" @default.
- W2022203019 startingPage "1783" @default.
- W2022203019 abstract "Under the assumption of weak perspective, two views of the same planar object are related through an affine transformation. In this paper, we consider the problem of training a simple neural network to learn to predict the parameters of the affine transformation. Although the proposed scheme has similarities with other neural network schemes, its practical advantages are more profound. First of all, the views used to train the neural network are not obtained by taking pictures of the object from different viewpoints. Instead, the training views are obtained by sampling the space of affine transformed views of the object. This space is constructed using a single view of the object. Fundamental to this procedure is a methodology, based on singular-value decomposition (SVD) and interval arithmetic (IA), for estimating the ranges of values that the parameters of affine transformation can assume. Second, the accuracy of the proposed scheme is very close to that of a traditional least squares approach with slightly better space and time requirements. A front-end stage to the neural network, based on principal components analysis (PCA), shows to increase its noise tolerance dramatically and also to guides us in deciding how many training views are necessary in order for the network to learn a good, noise tolerant, mapping. The proposed approach has been tested using both artificial and real data." @default.
- W2022203019 created "2016-06-24" @default.
- W2022203019 creator A5016844866 @default.
- W2022203019 creator A5030469716 @default.
- W2022203019 creator A5036799400 @default.
- W2022203019 creator A5088272059 @default.
- W2022203019 date "1999-10-01" @default.
- W2022203019 modified "2023-10-02" @default.
- W2022203019 title "Learning affine transformations" @default.
- W2022203019 cites W1483874187 @default.
- W2022203019 cites W1833887655 @default.
- W2022203019 cites W1877791080 @default.
- W2022203019 cites W1964262399 @default.
- W2022203019 cites W1980517342 @default.
- W2022203019 cites W2015902296 @default.
- W2022203019 cites W2024683548 @default.
- W2022203019 cites W2033554200 @default.
- W2022203019 cites W2040198157 @default.
- W2022203019 cites W2053197265 @default.
- W2022203019 cites W2072738093 @default.
- W2022203019 cites W2079999842 @default.
- W2022203019 cites W2080362491 @default.
- W2022203019 cites W2086479969 @default.
- W2022203019 cites W2117443967 @default.
- W2022203019 cites W2133671888 @default.
- W2022203019 cites W2159709546 @default.
- W2022203019 cites W2163535310 @default.
- W2022203019 cites W2169949933 @default.
- W2022203019 cites W2170625182 @default.
- W2022203019 doi "https://doi.org/10.1016/s0031-3203(98)00178-2" @default.
- W2022203019 hasPublicationYear "1999" @default.
- W2022203019 type Work @default.
- W2022203019 sameAs 2022203019 @default.
- W2022203019 citedByCount "26" @default.
- W2022203019 countsByYear W20222030192013 @default.
- W2022203019 countsByYear W20222030192014 @default.
- W2022203019 countsByYear W20222030192016 @default.
- W2022203019 countsByYear W20222030192019 @default.
- W2022203019 countsByYear W20222030192020 @default.
- W2022203019 countsByYear W20222030192021 @default.
- W2022203019 countsByYear W20222030192023 @default.
- W2022203019 crossrefType "journal-article" @default.
- W2022203019 hasAuthorship W2022203019A5016844866 @default.
- W2022203019 hasAuthorship W2022203019A5030469716 @default.
- W2022203019 hasAuthorship W2022203019A5036799400 @default.
- W2022203019 hasAuthorship W2022203019A5088272059 @default.
- W2022203019 hasConcept C104317684 @default.
- W2022203019 hasConcept C11413529 @default.
- W2022203019 hasConcept C153180895 @default.
- W2022203019 hasConcept C154945302 @default.
- W2022203019 hasConcept C18516315 @default.
- W2022203019 hasConcept C185592680 @default.
- W2022203019 hasConcept C204241405 @default.
- W2022203019 hasConcept C207221997 @default.
- W2022203019 hasConcept C22789450 @default.
- W2022203019 hasConcept C2524010 @default.
- W2022203019 hasConcept C2781238097 @default.
- W2022203019 hasConcept C33923547 @default.
- W2022203019 hasConcept C41008148 @default.
- W2022203019 hasConcept C50644808 @default.
- W2022203019 hasConcept C55493867 @default.
- W2022203019 hasConcept C92757383 @default.
- W2022203019 hasConceptScore W2022203019C104317684 @default.
- W2022203019 hasConceptScore W2022203019C11413529 @default.
- W2022203019 hasConceptScore W2022203019C153180895 @default.
- W2022203019 hasConceptScore W2022203019C154945302 @default.
- W2022203019 hasConceptScore W2022203019C18516315 @default.
- W2022203019 hasConceptScore W2022203019C185592680 @default.
- W2022203019 hasConceptScore W2022203019C204241405 @default.
- W2022203019 hasConceptScore W2022203019C207221997 @default.
- W2022203019 hasConceptScore W2022203019C22789450 @default.
- W2022203019 hasConceptScore W2022203019C2524010 @default.
- W2022203019 hasConceptScore W2022203019C2781238097 @default.
- W2022203019 hasConceptScore W2022203019C33923547 @default.
- W2022203019 hasConceptScore W2022203019C41008148 @default.
- W2022203019 hasConceptScore W2022203019C50644808 @default.
- W2022203019 hasConceptScore W2022203019C55493867 @default.
- W2022203019 hasConceptScore W2022203019C92757383 @default.
- W2022203019 hasIssue "10" @default.
- W2022203019 hasLocation W20222030191 @default.
- W2022203019 hasOpenAccess W2022203019 @default.
- W2022203019 hasPrimaryLocation W20222030191 @default.
- W2022203019 hasRelatedWork W1986076254 @default.
- W2022203019 hasRelatedWork W2038416447 @default.
- W2022203019 hasRelatedWork W2077614002 @default.
- W2022203019 hasRelatedWork W2100544925 @default.
- W2022203019 hasRelatedWork W2100815221 @default.
- W2022203019 hasRelatedWork W2122225529 @default.
- W2022203019 hasRelatedWork W2129598289 @default.
- W2022203019 hasRelatedWork W2184784635 @default.
- W2022203019 hasRelatedWork W2327965967 @default.
- W2022203019 hasRelatedWork W2364151838 @default.
- W2022203019 hasVolume "32" @default.
- W2022203019 isParatext "false" @default.
- W2022203019 isRetracted "false" @default.
- W2022203019 magId "2022203019" @default.
- W2022203019 workType "article" @default.