Matches in SemOpenAlex for { <https://semopenalex.org/work/W2556472504> ?p ?o ?g. }
- W2556472504 endingPage "53" @default.
- W2556472504 startingPage "45" @default.
- W2556472504 abstract "In recent years, learning based hashing becomes an attractive technique in large-scale image retrieval due to its low storage and computation cost. Hashing methods map each high-dimensional vector onto a low-dimensional hamming space by projection operators. However, when processing high dimensional data retrieval, many existing methods including hashing cost a majority of time on projection operators. In this paper, we solve this problem by implementing a sparsity regularizer. On one hand, due to the sparse property of the projection matrix, our method effectively lower both the storage and computation cost. On the other hand, we reduce the effective number of parameters involved in the learned projection matrix according to sparsity regularizer, which helps avoid overfitting problem. Without relaxing binary constraints, an iterative scheme jointly optimizing the objective function directly was given, which helps to obtain effective and efficient binary codes. We evaluate our method on three databases and compare it with some state-of-the-art hashing methods. Experimental results demonstrate that our method outperforms the comparison approaches." @default.
- W2556472504 created "2016-11-30" @default.
- W2556472504 creator A5001865165 @default.
- W2556472504 creator A5006886150 @default.
- W2556472504 creator A5009074046 @default.
- W2556472504 creator A5017774638 @default.
- W2556472504 creator A5066645546 @default.
- W2556472504 creator A5074492050 @default.
- W2556472504 date "2017-03-01" @default.
- W2556472504 modified "2023-10-14" @default.
- W2556472504 title "Large-scale image retrieval with supervised sparse hashing" @default.
- W2556472504 cites W1566135517 @default.
- W2556472504 cites W1910300841 @default.
- W2556472504 cites W1951226114 @default.
- W2556472504 cites W1972311232 @default.
- W2556472504 cites W1978333359 @default.
- W2556472504 cites W1980454827 @default.
- W2556472504 cites W1986931325 @default.
- W2556472504 cites W1992371516 @default.
- W2556472504 cites W2001535996 @default.
- W2556472504 cites W2029205712 @default.
- W2556472504 cites W2035626876 @default.
- W2556472504 cites W2036924016 @default.
- W2556472504 cites W2037351102 @default.
- W2556472504 cites W2043420811 @default.
- W2556472504 cites W2049993534 @default.
- W2556472504 cites W2051068426 @default.
- W2556472504 cites W2055906546 @default.
- W2556472504 cites W2056566623 @default.
- W2556472504 cites W2061736157 @default.
- W2556472504 cites W2074668987 @default.
- W2556472504 cites W2079202281 @default.
- W2556472504 cites W2084363474 @default.
- W2556472504 cites W2086504823 @default.
- W2556472504 cites W2108598243 @default.
- W2556472504 cites W2113180829 @default.
- W2556472504 cites W2113606819 @default.
- W2556472504 cites W2124386111 @default.
- W2556472504 cites W2126210882 @default.
- W2556472504 cites W2135364649 @default.
- W2556472504 cites W2144892774 @default.
- W2556472504 cites W2145065594 @default.
- W2556472504 cites W2157640836 @default.
- W2556472504 cites W2162006472 @default.
- W2556472504 cites W2162881463 @default.
- W2556472504 cites W2171790913 @default.
- W2556472504 cites W2173930701 @default.
- W2556472504 cites W2197084977 @default.
- W2556472504 cites W2202639555 @default.
- W2556472504 cites W2251084241 @default.
- W2556472504 cites W3098959905 @default.
- W2556472504 cites W3106512200 @default.
- W2556472504 cites W341506139 @default.
- W2556472504 cites W41027960 @default.
- W2556472504 cites W4236137412 @default.
- W2556472504 doi "https://doi.org/10.1016/j.neucom.2016.05.109" @default.
- W2556472504 hasPublicationYear "2017" @default.
- W2556472504 type Work @default.
- W2556472504 sameAs 2556472504 @default.
- W2556472504 citedByCount "17" @default.
- W2556472504 countsByYear W25564725042017 @default.
- W2556472504 countsByYear W25564725042018 @default.
- W2556472504 countsByYear W25564725042019 @default.
- W2556472504 countsByYear W25564725042021 @default.
- W2556472504 countsByYear W25564725042022 @default.
- W2556472504 countsByYear W25564725042023 @default.
- W2556472504 crossrefType "journal-article" @default.
- W2556472504 hasAuthorship W2556472504A5001865165 @default.
- W2556472504 hasAuthorship W2556472504A5006886150 @default.
- W2556472504 hasAuthorship W2556472504A5009074046 @default.
- W2556472504 hasAuthorship W2556472504A5017774638 @default.
- W2556472504 hasAuthorship W2556472504A5066645546 @default.
- W2556472504 hasAuthorship W2556472504A5074492050 @default.
- W2556472504 hasConcept C11413529 @default.
- W2556472504 hasConcept C115961682 @default.
- W2556472504 hasConcept C116058348 @default.
- W2556472504 hasConcept C122907437 @default.
- W2556472504 hasConcept C133667856 @default.
- W2556472504 hasConcept C138111711 @default.
- W2556472504 hasConcept C153180895 @default.
- W2556472504 hasConcept C154945302 @default.
- W2556472504 hasConcept C157125643 @default.
- W2556472504 hasConcept C1667742 @default.
- W2556472504 hasConcept C187062812 @default.
- W2556472504 hasConcept C193319292 @default.
- W2556472504 hasConcept C22019652 @default.
- W2556472504 hasConcept C2779494224 @default.
- W2556472504 hasConcept C38652104 @default.
- W2556472504 hasConcept C41008148 @default.
- W2556472504 hasConcept C45374587 @default.
- W2556472504 hasConcept C50644808 @default.
- W2556472504 hasConcept C57273362 @default.
- W2556472504 hasConcept C57493831 @default.
- W2556472504 hasConcept C67388219 @default.
- W2556472504 hasConcept C73150493 @default.
- W2556472504 hasConcept C99138194 @default.
- W2556472504 hasConceptScore W2556472504C11413529 @default.
- W2556472504 hasConceptScore W2556472504C115961682 @default.