FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2696471905> ?p ?o ?g. }

• W2696471905 endingPage "2992" @default.
• W2696471905 startingPage "2978" @default.
• W2696471905 abstract "Correspondence problems are challenging due to the complexity of real-world scenes. One way to solve this problem is to improve the graph matching (GM) process, which is flexible for matching non-rigid objects. GM can be classified into three categories that correspond with the variety of object functions: first-order, second-order, and high-order matching. Graph and hypergraph matching have been proposed separately in previous works. The former is equivalent to the second-order GM, and the latter is equivalent to high-order GM, but we use the terms second- and high-order GM to unify the terminology in this paper. Second- and high-order GM fit well with different types of problems; the key goal for these processes is to find better-optimized algorithms. Because the optimal problems for second- and high-order GM are different, we propose two novel optimized algorithms for them in this paper. (1) For the second-order GM, we first introduce a <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$K$ </tex-math></inline-formula> -nearest-neighbor-pooling matching method that integrates feature pooling into GM and reduces the complexity. Meanwhile, we evaluate each matching candidate using discriminative weights on its <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$k$ </tex-math></inline-formula> -nearest neighbors by taking locality as well as sparsity into consideration. (2) High-order GM introduces numerous outliers, because precision is rarely considered in related methods. Therefore, we propose a sub-pattern structure to construct a robust high-order GM method that better integrates geometric information. To narrow the search space and solve the optimization problem, a new prior strategy and a cell-algorithm-based Markov Chain Monte Carlo framework are proposed. In addition, experiments demonstrate the robustness and improvements of these algorithms with respect to matching accuracy compared with other state-of-the-art algorithms." @default.
• W2696471905 created "2017-06-30" @default.
• W2696471905 creator A5017052768 @default.
• W2696471905 creator A5032881192 @default.
• W2696471905 date "2018-10-01" @default.
• W2696471905 modified "2023-10-16" @default.
• W2696471905 title "Second- and High-Order Graph Matching for Correspondence Problems" @default.
• W2696471905 cites W1508951912 @default.
• W2696471905 cites W1582614941 @default.
• W2696471905 cites W1587878450 @default.
• W2696471905 cites W1589216124 @default.
• W2696471905 cites W1868020197 @default.
• W2696471905 cites W1917573513 @default.
• W2696471905 cites W1976466396 @default.
• W2696471905 cites W1988650493 @default.
• W2696471905 cites W1998840160 @default.
• W2696471905 cites W2027922120 @default.
• W2696471905 cites W2032732073 @default.
• W2696471905 cites W2034007935 @default.
• W2696471905 cites W2048971218 @default.
• W2696471905 cites W2068078373 @default.
• W2696471905 cites W2078501237 @default.
• W2696471905 cites W2079272365 @default.
• W2696471905 cites W2094539604 @default.
• W2696471905 cites W2109294083 @default.
• W2696471905 cites W2120419212 @default.
• W2696471905 cites W2121225280 @default.
• W2696471905 cites W2136796925 @default.
• W2696471905 cites W2137275576 @default.
• W2696471905 cites W2138910149 @default.
• W2696471905 cites W2142726150 @default.
• W2696471905 cites W2145544188 @default.
• W2696471905 cites W2150760714 @default.
• W2696471905 cites W2161914072 @default.
• W2696471905 cites W2165497495 @default.
• W2696471905 cites W2166820607 @default.
• W2696471905 cites W2168002178 @default.
• W2696471905 cites W2207282238 @default.
• W2696471905 cites W2211710464 @default.
• W2696471905 cites W2552833909 @default.
• W2696471905 cites W2552972371 @default.
• W2696471905 cites W3103722964 @default.
• W2696471905 cites W35665245 @default.
• W2696471905 cites W4243684731 @default.
• W2696471905 cites W7408119 @default.
• W2696471905 cites W89005514 @default.
• W2696471905 doi "https://doi.org/10.1109/tcsvt.2017.2718225" @default.
• W2696471905 hasPublicationYear "2018" @default.
• W2696471905 type Work @default.
• W2696471905 sameAs 2696471905 @default.
• W2696471905 citedByCount "24" @default.
• W2696471905 countsByYear W26964719052018 @default.
• W2696471905 countsByYear W26964719052019 @default.
• W2696471905 countsByYear W26964719052020 @default.
• W2696471905 countsByYear W26964719052021 @default.
• W2696471905 countsByYear W26964719052022 @default.
• W2696471905 countsByYear W26964719052023 @default.
• W2696471905 crossrefType "journal-article" @default.
• W2696471905 hasAuthorship W2696471905A5017052768 @default.
• W2696471905 hasAuthorship W2696471905A5032881192 @default.
• W2696471905 hasConcept C10138342 @default.
• W2696471905 hasConcept C105795698 @default.
• W2696471905 hasConcept C114614502 @default.
• W2696471905 hasConcept C154945302 @default.
• W2696471905 hasConcept C162324750 @default.
• W2696471905 hasConcept C165064840 @default.
• W2696471905 hasConcept C182306322 @default.
• W2696471905 hasConcept C191399111 @default.
• W2696471905 hasConcept C2781221856 @default.
• W2696471905 hasConcept C33923547 @default.
• W2696471905 hasConcept C41008148 @default.
• W2696471905 hasConcept C45357846 @default.
• W2696471905 hasConcept C70437156 @default.
• W2696471905 hasConcept C80444323 @default.
• W2696471905 hasConcept C94375191 @default.
• W2696471905 hasConceptScore W2696471905C10138342 @default.
• W2696471905 hasConceptScore W2696471905C105795698 @default.
• W2696471905 hasConceptScore W2696471905C114614502 @default.
• W2696471905 hasConceptScore W2696471905C154945302 @default.
• W2696471905 hasConceptScore W2696471905C162324750 @default.
• W2696471905 hasConceptScore W2696471905C165064840 @default.
• W2696471905 hasConceptScore W2696471905C182306322 @default.
• W2696471905 hasConceptScore W2696471905C191399111 @default.
• W2696471905 hasConceptScore W2696471905C2781221856 @default.
• W2696471905 hasConceptScore W2696471905C33923547 @default.
• W2696471905 hasConceptScore W2696471905C41008148 @default.
• W2696471905 hasConceptScore W2696471905C45357846 @default.
• W2696471905 hasConceptScore W2696471905C70437156 @default.
• W2696471905 hasConceptScore W2696471905C80444323 @default.
• W2696471905 hasConceptScore W2696471905C94375191 @default.
• W2696471905 hasFunder F4320335790 @default.
• W2696471905 hasIssue "10" @default.
• W2696471905 hasLocation W26964719051 @default.
• W2696471905 hasOpenAccess W2696471905 @default.
• W2696471905 hasPrimaryLocation W26964719051 @default.
• W2696471905 hasRelatedWork W2083155064 @default.
• W2696471905 hasRelatedWork W2903973362 @default.
• W2696471905 hasRelatedWork W2953272193 @default.

• next