FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2023443487> ?p ?o ?g. }

• W2023443487 endingPage "112" @default.
• W2023443487 startingPage "91" @default.
• W2023443487 abstract "It is well known that natural images admit sparse representations by redundant dictionaries of basis functions such as Gabor-like wavelets. However, it is still an open question as to what the next layer of representational units above the layer of wavelets should be. We address this fundamental question by proposing a sparse FRAME (Filters, Random field, And Maximum Entropy) model for representing natural image patterns. Our sparse FRAME model is an inhomogeneous generalization of the original FRAME model. It is a non-stationary Markov random field model that reproduces the observed statistical properties of filter responses at a subset of selected locations, scales and orientations. Each sparse FRAME model is intended to represent an object pattern and can be considered a deformable template. The sparse FRAME model can be written as a shared sparse coding model, which motivates us to propose a two-stage algorithm for learning the model. The first stage selects the subset of wavelets from the dictionary by a shared matching pursuit algorithm. The second stage then estimates the parameters of the model given the selected wavelets. Our experiments show that the sparse FRAME models are capable of representing a wide variety of object patterns in natural images and that the learned models are useful for object classification." @default.
• W2023443487 created "2016-06-24" @default.
• W2023443487 creator A5015720040 @default.
• W2023443487 creator A5034228010 @default.
• W2023443487 creator A5041455283 @default.
• W2023443487 creator A5055935194 @default.
• W2023443487 date "2014-10-02" @default.
• W2023443487 modified "2023-09-25" @default.
• W2023443487 title "Learning Sparse FRAME Models for Natural Image Patterns" @default.
• W2023443487 cites W1513873506 @default.
• W2023443487 cites W1722318740 @default.
• W2023443487 cites W1821057786 @default.
• W2023443487 cites W1964724001 @default.
• W2023443487 cites W1974774078 @default.
• W2023443487 cites W1976709621 @default.
• W2023443487 cites W1983334819 @default.
• W2023443487 cites W1985967702 @default.
• W2023443487 cites W1990838964 @default.
• W2023443487 cites W2009703350 @default.
• W2023443487 cites W2013164703 @default.
• W2023443487 cites W2020636921 @default.
• W2023443487 cites W2020999234 @default.
• W2023443487 cites W2042492924 @default.
• W2023443487 cites W2058605740 @default.
• W2023443487 cites W2059448777 @default.
• W2023443487 cites W2077669678 @default.
• W2023443487 cites W2078204800 @default.
• W2023443487 cites W2079930597 @default.
• W2023443487 cites W2081895856 @default.
• W2023443487 cites W2099321050 @default.
• W2023443487 cites W2107844156 @default.
• W2023443487 cites W2116064496 @default.
• W2023443487 cites W2125536150 @default.
• W2023443487 cites W2128053425 @default.
• W2023443487 cites W2128659236 @default.
• W2023443487 cites W2130184048 @default.
• W2023443487 cites W2130325614 @default.
• W2023443487 cites W2130481596 @default.
• W2023443487 cites W2136922672 @default.
• W2023443487 cites W2141200610 @default.
• W2023443487 cites W2145169631 @default.
• W2023443487 cites W2145889472 @default.
• W2023443487 cites W2149194912 @default.
• W2023443487 cites W2151103935 @default.
• W2023443487 cites W2151693816 @default.
• W2023443487 cites W2153663612 @default.
• W2023443487 cites W2157785665 @default.
• W2023443487 cites W2160547390 @default.
• W2023443487 cites W2160842254 @default.
• W2023443487 cites W2161969291 @default.
• W2023443487 cites W2162915993 @default.
• W2023443487 cites W2163922914 @default.
• W2023443487 cites W2165181841 @default.
• W2023443487 cites W2168356304 @default.
• W2023443487 cites W2954040150 @default.
• W2023443487 cites W3099751318 @default.
• W2023443487 cites W4205969993 @default.
• W2023443487 cites W4230674625 @default.
• W2023443487 cites W4235713725 @default.
• W2023443487 cites W4252182960 @default.
• W2023443487 doi "https://doi.org/10.1007/s11263-014-0757-x" @default.
• W2023443487 hasPublicationYear "2014" @default.
• W2023443487 type Work @default.
• W2023443487 sameAs 2023443487 @default.
• W2023443487 citedByCount "39" @default.
• W2023443487 countsByYear W20234434872015 @default.
• W2023443487 countsByYear W20234434872016 @default.
• W2023443487 countsByYear W20234434872017 @default.
• W2023443487 countsByYear W20234434872018 @default.
• W2023443487 countsByYear W20234434872019 @default.
• W2023443487 countsByYear W20234434872020 @default.
• W2023443487 countsByYear W20234434872021 @default.
• W2023443487 countsByYear W20234434872022 @default.
• W2023443487 crossrefType "journal-article" @default.
• W2023443487 hasAuthorship W2023443487A5015720040 @default.
• W2023443487 hasAuthorship W2023443487A5034228010 @default.
• W2023443487 hasAuthorship W2023443487A5041455283 @default.
• W2023443487 hasAuthorship W2023443487A5055935194 @default.
• W2023443487 hasBestOaLocation W20234434872 @default.
• W2023443487 hasConcept C115961682 @default.
• W2023443487 hasConcept C124066611 @default.
• W2023443487 hasConcept C124504099 @default.
• W2023443487 hasConcept C124851039 @default.
• W2023443487 hasConcept C126042441 @default.
• W2023443487 hasConcept C136902061 @default.
• W2023443487 hasConcept C153180895 @default.
• W2023443487 hasConcept C154945302 @default.
• W2023443487 hasConcept C156872377 @default.
• W2023443487 hasConcept C167966045 @default.
• W2023443487 hasConcept C196216189 @default.
• W2023443487 hasConcept C2778045648 @default.
• W2023443487 hasConcept C2779883129 @default.
• W2023443487 hasConcept C31972630 @default.
• W2023443487 hasConcept C33923547 @default.
• W2023443487 hasConcept C39890363 @default.
• W2023443487 hasConcept C41008148 @default.
• W2023443487 hasConcept C46286280 @default.
• W2023443487 hasConcept C47432892 @default.

• next