Matches in SemOpenAlex for { <https://semopenalex.org/work/W2002163407> ?p ?o ?g. }
- W2002163407 endingPage "3168" @default.
- W2002163407 startingPage "3160" @default.
- W2002163407 abstract "High dimensional dense features have been shown to be useful for face recognition, but result in high query time when searching a large-scale face database. Hence binary codes are often used to obtain fast query speeds as well as reduce storage requirements. However, binary codes for face features can become unstable and unpredictable due to face variations induced by pose, expression and illumination. This paper proposes a predictable hash code algorithm to map face samples in the original feature space to Hamming space. First, we discuss the 'predictability' of hash codes for face indexing. Second, we formulate the predictable hash coding problem as a non-convex combinatorial optimization problem, in which the distance between codes for samples from the same class is minimized while the distance between codes for samples from different classes is maximized. An Expectation Maximization method is introduced to iteratively find a sparse and predictable linear mapping. Lastly, a deep feature representation is learned to further enhance the predictability of binary codes. Experimental results on three commonly used face databases demonstrate the superiority of our predictable hash coding algorithm on large-scale problems. HighlightsDiscussing the 'predictability' of binary codes for face indexing.A non-convex combinatorial optimization problem solved with EM method.Applying CNN to learn a deep face representation.Achieving state-of-the-art results on the YouTube Celebrities dataset." @default.
- W2002163407 created "2016-06-24" @default.
- W2002163407 creator A5032038866 @default.
- W2002163407 creator A5050146220 @default.
- W2002163407 creator A5055264952 @default.
- W2002163407 creator A5078748099 @default.
- W2002163407 date "2015-10-01" @default.
- W2002163407 modified "2023-10-16" @default.
- W2002163407 title "Learning predictable binary codes for face indexing" @default.
- W2002163407 cites W1468978781 @default.
- W2002163407 cites W1705126064 @default.
- W2002163407 cites W1781921453 @default.
- W2002163407 cites W1846470281 @default.
- W2002163407 cites W1970055505 @default.
- W2002163407 cites W1976258951 @default.
- W2002163407 cites W1977774297 @default.
- W2002163407 cites W1988984481 @default.
- W2002163407 cites W1989902617 @default.
- W2002163407 cites W1992371516 @default.
- W2002163407 cites W1998808035 @default.
- W2002163407 cites W2005539193 @default.
- W2002163407 cites W2019041733 @default.
- W2002163407 cites W2021340975 @default.
- W2002163407 cites W2022398315 @default.
- W2002163407 cites W2029205712 @default.
- W2002163407 cites W2038233937 @default.
- W2002163407 cites W2042749939 @default.
- W2002163407 cites W2044195942 @default.
- W2002163407 cites W2048387976 @default.
- W2002163407 cites W2061441693 @default.
- W2002163407 cites W2084363474 @default.
- W2002163407 cites W2088009615 @default.
- W2002163407 cites W2114588272 @default.
- W2002163407 cites W2118622097 @default.
- W2002163407 cites W2124509324 @default.
- W2002163407 cites W2126960670 @default.
- W2002163407 cites W2129812935 @default.
- W2002163407 cites W2134514757 @default.
- W2002163407 cites W2137659841 @default.
- W2002163407 cites W2137823674 @default.
- W2002163407 cites W2145287260 @default.
- W2002163407 cites W2150600350 @default.
- W2002163407 cites W2153273131 @default.
- W2002163407 cites W2156395823 @default.
- W2002163407 cites W2163922914 @default.
- W2002163407 cites W2164530430 @default.
- W2002163407 cites W2171790913 @default.
- W2002163407 doi "https://doi.org/10.1016/j.patcog.2015.03.016" @default.
- W2002163407 hasPublicationYear "2015" @default.
- W2002163407 type Work @default.
- W2002163407 sameAs 2002163407 @default.
- W2002163407 citedByCount "27" @default.
- W2002163407 countsByYear W20021634072015 @default.
- W2002163407 countsByYear W20021634072016 @default.
- W2002163407 countsByYear W20021634072017 @default.
- W2002163407 countsByYear W20021634072018 @default.
- W2002163407 countsByYear W20021634072019 @default.
- W2002163407 countsByYear W20021634072020 @default.
- W2002163407 countsByYear W20021634072022 @default.
- W2002163407 countsByYear W20021634072023 @default.
- W2002163407 crossrefType "journal-article" @default.
- W2002163407 hasAuthorship W2002163407A5032038866 @default.
- W2002163407 hasAuthorship W2002163407A5050146220 @default.
- W2002163407 hasAuthorship W2002163407A5055264952 @default.
- W2002163407 hasAuthorship W2002163407A5078748099 @default.
- W2002163407 hasConcept C144024400 @default.
- W2002163407 hasConcept C154945302 @default.
- W2002163407 hasConcept C2779304628 @default.
- W2002163407 hasConcept C33923547 @default.
- W2002163407 hasConcept C36289849 @default.
- W2002163407 hasConcept C41008148 @default.
- W2002163407 hasConcept C48372109 @default.
- W2002163407 hasConcept C75165309 @default.
- W2002163407 hasConcept C94375191 @default.
- W2002163407 hasConceptScore W2002163407C144024400 @default.
- W2002163407 hasConceptScore W2002163407C154945302 @default.
- W2002163407 hasConceptScore W2002163407C2779304628 @default.
- W2002163407 hasConceptScore W2002163407C33923547 @default.
- W2002163407 hasConceptScore W2002163407C36289849 @default.
- W2002163407 hasConceptScore W2002163407C41008148 @default.
- W2002163407 hasConceptScore W2002163407C48372109 @default.
- W2002163407 hasConceptScore W2002163407C75165309 @default.
- W2002163407 hasConceptScore W2002163407C94375191 @default.
- W2002163407 hasFunder F4320321001 @default.
- W2002163407 hasFunder F4320335777 @default.
- W2002163407 hasIssue "10" @default.
- W2002163407 hasLocation W20021634071 @default.
- W2002163407 hasOpenAccess W2002163407 @default.
- W2002163407 hasPrimaryLocation W20021634071 @default.
- W2002163407 hasRelatedWork W1527777418 @default.
- W2002163407 hasRelatedWork W1551728297 @default.
- W2002163407 hasRelatedWork W1599408952 @default.
- W2002163407 hasRelatedWork W1607840445 @default.
- W2002163407 hasRelatedWork W1636112402 @default.
- W2002163407 hasRelatedWork W1873761914 @default.
- W2002163407 hasRelatedWork W1991645216 @default.
- W2002163407 hasRelatedWork W2111308187 @default.
- W2002163407 hasRelatedWork W2348101466 @default.