Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895943854> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2895943854 abstract "While encouraging results have been made so far to advance kinship verification by using facial images, learning a robust genetic similarity measure remains challenging, especially in the setting of general kinship verification, wherein the gender labels of the test samples are unknown in advance. In this paper we present a deep metric learning method with a carefully designed two-stream neural network to jointly learn a pair of deep embeddings for parent-child images. In particular, the deep embeddings are first modeled to explicitly consist of the common and individual components, and then two additional constraints are introduced in deep metric learning: 1) value-aware consistency on the common components, and 2) position-aware exclusivity on the individual components. The proposed hierarchical consistency-exclusivity regularization enables our deep metric learning to harness the sharable and complementary patterns inherent in parent-child images. Empirically, we show improved performance over state of the art metric learning solutions to general kinship verification on two benchmarks." @default.
- W2895943854 created "2018-10-26" @default.
- W2895943854 creator A5008461360 @default.
- W2895943854 creator A5053602127 @default.
- W2895943854 creator A5085431435 @default.
- W2895943854 creator A5088888083 @default.
- W2895943854 creator A5089109391 @default.
- W2895943854 date "2018-07-01" @default.
- W2895943854 modified "2023-10-09" @default.
- W2895943854 title "Consistency-Exclusivity Regularized Deep Metric Learning for General Kinship Verification" @default.
- W2895943854 cites W1972014290 @default.
- W2895943854 cites W1996337501 @default.
- W2895943854 cites W1998230826 @default.
- W2895943854 cites W2047186200 @default.
- W2895943854 cites W2076434944 @default.
- W2895943854 cites W2079742827 @default.
- W2895943854 cites W2100549954 @default.
- W2895943854 cites W2108909793 @default.
- W2895943854 cites W2112999064 @default.
- W2895943854 cites W2117154949 @default.
- W2895943854 cites W2125911081 @default.
- W2895943854 cites W2132886138 @default.
- W2895943854 cites W2145773134 @default.
- W2895943854 cites W2207044458 @default.
- W2895943854 cites W2560852071 @default.
- W2895943854 cites W2564325886 @default.
- W2895943854 cites W2679426462 @default.
- W2895943854 cites W2753064086 @default.
- W2895943854 cites W2758388116 @default.
- W2895943854 cites W3105535737 @default.
- W2895943854 doi "https://doi.org/10.1109/icme.2018.8486590" @default.
- W2895943854 hasPublicationYear "2018" @default.
- W2895943854 type Work @default.
- W2895943854 sameAs 2895943854 @default.
- W2895943854 citedByCount "1" @default.
- W2895943854 countsByYear W28959438542019 @default.
- W2895943854 crossrefType "proceedings-article" @default.
- W2895943854 hasAuthorship W2895943854A5008461360 @default.
- W2895943854 hasAuthorship W2895943854A5053602127 @default.
- W2895943854 hasAuthorship W2895943854A5085431435 @default.
- W2895943854 hasAuthorship W2895943854A5088888083 @default.
- W2895943854 hasAuthorship W2895943854A5089109391 @default.
- W2895943854 hasConcept C103278499 @default.
- W2895943854 hasConcept C108583219 @default.
- W2895943854 hasConcept C115961682 @default.
- W2895943854 hasConcept C119857082 @default.
- W2895943854 hasConcept C127413603 @default.
- W2895943854 hasConcept C144348335 @default.
- W2895943854 hasConcept C154945302 @default.
- W2895943854 hasConcept C176217482 @default.
- W2895943854 hasConcept C17744445 @default.
- W2895943854 hasConcept C199539241 @default.
- W2895943854 hasConcept C21547014 @default.
- W2895943854 hasConcept C2776135515 @default.
- W2895943854 hasConcept C2776436953 @default.
- W2895943854 hasConcept C2984842247 @default.
- W2895943854 hasConcept C41008148 @default.
- W2895943854 hasConcept C50644808 @default.
- W2895943854 hasConcept C80444323 @default.
- W2895943854 hasConceptScore W2895943854C103278499 @default.
- W2895943854 hasConceptScore W2895943854C108583219 @default.
- W2895943854 hasConceptScore W2895943854C115961682 @default.
- W2895943854 hasConceptScore W2895943854C119857082 @default.
- W2895943854 hasConceptScore W2895943854C127413603 @default.
- W2895943854 hasConceptScore W2895943854C144348335 @default.
- W2895943854 hasConceptScore W2895943854C154945302 @default.
- W2895943854 hasConceptScore W2895943854C176217482 @default.
- W2895943854 hasConceptScore W2895943854C17744445 @default.
- W2895943854 hasConceptScore W2895943854C199539241 @default.
- W2895943854 hasConceptScore W2895943854C21547014 @default.
- W2895943854 hasConceptScore W2895943854C2776135515 @default.
- W2895943854 hasConceptScore W2895943854C2776436953 @default.
- W2895943854 hasConceptScore W2895943854C2984842247 @default.
- W2895943854 hasConceptScore W2895943854C41008148 @default.
- W2895943854 hasConceptScore W2895943854C50644808 @default.
- W2895943854 hasConceptScore W2895943854C80444323 @default.
- W2895943854 hasLocation W28959438541 @default.
- W2895943854 hasOpenAccess W2895943854 @default.
- W2895943854 hasPrimaryLocation W28959438541 @default.
- W2895943854 hasRelatedWork W2604802223 @default.
- W2895943854 hasRelatedWork W2791691546 @default.
- W2895943854 hasRelatedWork W2801467094 @default.
- W2895943854 hasRelatedWork W2895943854 @default.
- W2895943854 hasRelatedWork W2950066684 @default.
- W2895943854 hasRelatedWork W2978367927 @default.
- W2895943854 hasRelatedWork W3034749675 @default.
- W2895943854 hasRelatedWork W3124304076 @default.
- W2895943854 hasRelatedWork W3174422331 @default.
- W2895943854 hasRelatedWork W3179488938 @default.
- W2895943854 isParatext "false" @default.
- W2895943854 isRetracted "false" @default.
- W2895943854 magId "2895943854" @default.
- W2895943854 workType "article" @default.