FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2155608052> ?p ?o ?g. }

• W2155608052 endingPage "3124" @default.
• W2155608052 startingPage "3113" @default.
• W2155608052 abstract "Face recognition on large-scale video in the wild is becoming increasingly important due to the ubiquity of video data captured by surveillance cameras, handheld devices, Internet uploads, and other sources. By treating each video as one image set, set-based methods recently have made great success in the field of video-based face recognition. In the wild world, videos often contain extremely complex data variations and thus pose a big challenge of set modeling for set-based methods. In this paper, we propose a novel Hybrid Euclidean-and-Riemannian Metric Learning (HERML) method to fuse multiple statistics of image set. Specifically, we represent each image set simultaneously by mean, covariance matrix and Gaussian distribution, which generally complement each other in the aspect of set modeling. However, it is not trivial to fuse them since mean, covariance matrix and Gaussian model typically lie in multiple heterogeneous spaces equipped with Euclidean or Riemannian metric. Therefore, we first implicitly map the original statistics into high dimensional Hilbert spaces by exploiting Euclidean and Riemannian kernels. With a LogDet divergence based objective function, the hybrid kernels are then fused by our hybrid metric learning framework, which can efficiently perform the fusing procedure on large-scale videos. The proposed method is evaluated on four public and challenging large-scale video face datasets. Extensive experimental results demonstrate that our method has a clear superiority over the state-of-the-art set-based methods for large-scale video-based face recognition." @default.
• W2155608052 created "2016-06-24" @default.
• W2155608052 creator A5007688302 @default.
• W2155608052 creator A5038918043 @default.
• W2155608052 creator A5050297728 @default.
• W2155608052 creator A5083420537 @default.
• W2155608052 date "2015-10-01" @default.
• W2155608052 modified "2023-10-14" @default.
• W2155608052 title "Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning" @default.
• W2155608052 cites W1506778248 @default.
• W2155608052 cites W1549083695 @default.
• W2155608052 cites W1820849028 @default.
• W2155608052 cites W1862697533 @default.
• W2155608052 cites W1963589611 @default.
• W2155608052 cites W1983496390 @default.
• W2155608052 cites W1986964250 @default.
• W2155608052 cites W1996939238 @default.
• W2155608052 cites W1996955012 @default.
• W2155608052 cites W2000771160 @default.
• W2155608052 cites W2009119155 @default.
• W2155608052 cites W2019464758 @default.
• W2155608052 cites W2021340975 @default.
• W2155608052 cites W2022398315 @default.
• W2155608052 cites W2025341678 @default.
• W2155608052 cites W2033468335 @default.
• W2155608052 cites W2041657594 @default.
• W2155608052 cites W2056526820 @default.
• W2155608052 cites W2062811091 @default.
• W2155608052 cites W2066986622 @default.
• W2155608052 cites W2067940056 @default.
• W2155608052 cites W2071266191 @default.
• W2155608052 cites W2076434944 @default.
• W2155608052 cites W2079844951 @default.
• W2155608052 cites W2098805611 @default.
• W2155608052 cites W2102098892 @default.
• W2155608052 cites W2110744759 @default.
• W2155608052 cites W2111654153 @default.
• W2155608052 cites W2112695787 @default.
• W2155608052 cites W2116022929 @default.
• W2155608052 cites W2120453412 @default.
• W2155608052 cites W2122691893 @default.
• W2155608052 cites W2125027820 @default.
• W2155608052 cites W2126017757 @default.
• W2155608052 cites W2137894166 @default.
• W2155608052 cites W2141830256 @default.
• W2155608052 cites W2143159002 @default.
• W2155608052 cites W2144760012 @default.
• W2155608052 cites W2147147599 @default.
• W2155608052 cites W2149652297 @default.
• W2155608052 cites W2150600350 @default.
• W2155608052 cites W2161259116 @default.
• W2155608052 cites W2169495281 @default.
• W2155608052 cites W2169579681 @default.
• W2155608052 doi "https://doi.org/10.1016/j.patcog.2015.03.011" @default.
• W2155608052 hasPublicationYear "2015" @default.
• W2155608052 type Work @default.
• W2155608052 sameAs 2155608052 @default.
• W2155608052 citedByCount "70" @default.
• W2155608052 countsByYear W21556080522015 @default.
• W2155608052 countsByYear W21556080522016 @default.
• W2155608052 countsByYear W21556080522017 @default.
• W2155608052 countsByYear W21556080522018 @default.
• W2155608052 countsByYear W21556080522019 @default.
• W2155608052 countsByYear W21556080522020 @default.
• W2155608052 countsByYear W21556080522021 @default.
• W2155608052 countsByYear W21556080522022 @default.
• W2155608052 countsByYear W21556080522023 @default.
• W2155608052 crossrefType "journal-article" @default.
• W2155608052 hasAuthorship W2155608052A5007688302 @default.
• W2155608052 hasAuthorship W2155608052A5038918043 @default.
• W2155608052 hasAuthorship W2155608052A5050297728 @default.
• W2155608052 hasAuthorship W2155608052A5083420537 @default.
• W2155608052 hasBestOaLocation W21556080522 @default.
• W2155608052 hasConcept C120174047 @default.
• W2155608052 hasConcept C121332964 @default.
• W2155608052 hasConcept C153180895 @default.
• W2155608052 hasConcept C154945302 @default.
• W2155608052 hasConcept C162324750 @default.
• W2155608052 hasConcept C176217482 @default.
• W2155608052 hasConcept C21547014 @default.
• W2155608052 hasConcept C2778755073 @default.
• W2155608052 hasConcept C31510193 @default.
• W2155608052 hasConcept C31972630 @default.
• W2155608052 hasConcept C33923547 @default.
• W2155608052 hasConcept C41008148 @default.
• W2155608052 hasConcept C62520636 @default.
• W2155608052 hasConceptScore W2155608052C120174047 @default.
• W2155608052 hasConceptScore W2155608052C121332964 @default.
• W2155608052 hasConceptScore W2155608052C153180895 @default.
• W2155608052 hasConceptScore W2155608052C154945302 @default.
• W2155608052 hasConceptScore W2155608052C162324750 @default.
• W2155608052 hasConceptScore W2155608052C176217482 @default.
• W2155608052 hasConceptScore W2155608052C21547014 @default.
• W2155608052 hasConceptScore W2155608052C2778755073 @default.
• W2155608052 hasConceptScore W2155608052C31510193 @default.
• W2155608052 hasConceptScore W2155608052C31972630 @default.
• W2155608052 hasConceptScore W2155608052C33923547 @default.
• W2155608052 hasConceptScore W2155608052C41008148 @default.

• next