FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283013657> ?p ?o ?g. }

• W4283013657 endingPage "305" @default.
• W4283013657 startingPage "290" @default.
• W4283013657 abstract "Abstract Learning disentangled representation of data is a key problem in deep learning. Specifically, disentangling 2D facial landmarks into different factors ( e.g. , identity and expression) is widely used in the applications of face reconstruction, face reenactment and talking head et al. . However, due to the sparsity of landmarks and the lack of accurate labels for the factors, it is hard to learn the disentangled representation of landmarks. To address these problem, we propose a simple and effective model named FLD-VAE to disentangle arbitrary facial landmarks into identity and expression latent representations, which is based on a Variational Autoencoder framework. Besides, we propose three invariant loss functions in both latent and data levels to constrain the invariance of representations during training stage. Moreover, we implement an identity preservation loss to further enhance the representation ability of identity factor. To the best of our knowledge, this is the first work to end-to-end disentangle identity and expression factors simultaneously from one single facial landmark." @default.
• W4283013657 created "2022-06-18" @default.
• W4283013657 creator A5022732805 @default.
• W4283013657 creator A5050539684 @default.
• W4283013657 creator A5059021869 @default.
• W4283013657 creator A5071737735 @default.
• W4283013657 creator A5072440928 @default.
• W4283013657 creator A5083366771 @default.
• W4283013657 date "2022-06-01" @default.
• W4283013657 modified "2023-10-05" @default.
• W4283013657 title "Facial landmark disentangled network with variational autoencoder" @default.
• W4283013657 cites W2015143272 @default.
• W4283013657 cites W2062227835 @default.
• W4283013657 cites W2107037917 @default.
• W4283013657 cites W2130259898 @default.
• W4283013657 cites W2150283722 @default.
• W4283013657 cites W2237250383 @default.
• W4283013657 cites W2301937176 @default.
• W4283013657 cites W2471723840 @default.
• W4283013657 cites W2594690981 @default.
• W4283013657 cites W2611752399 @default.
• W4283013657 cites W2883221003 @default.
• W4283013657 cites W2895226286 @default.
• W4283013657 cites W2917887692 @default.
• W4283013657 cites W2945729334 @default.
• W4283013657 cites W2962770929 @default.
• W4283013657 cites W2963081548 @default.
• W4283013657 cites W2963290645 @default.
• W4283013657 cites W2963342110 @default.
• W4283013657 cites W2963409406 @default.
• W4283013657 cites W2969985801 @default.
• W4283013657 cites W2998185320 @default.
• W4283013657 cites W3034241236 @default.
• W4283013657 cites W3035052596 @default.
• W4283013657 cites W3035201761 @default.
• W4283013657 cites W3049460872 @default.
• W4283013657 cites W3087121792 @default.
• W4283013657 cites W3089455867 @default.
• W4283013657 cites W3098557217 @default.
• W4283013657 cites W3104792420 @default.
• W4283013657 cites W3107992834 @default.
• W4283013657 cites W3112871073 @default.
• W4283013657 cites W3120163087 @default.
• W4283013657 doi "https://doi.org/10.1007/s11766-022-4589-0" @default.
• W4283013657 hasPublicationYear "2022" @default.
• W4283013657 type Work @default.
• W4283013657 citedByCount "1" @default.
• W4283013657 countsByYear W42830136572022 @default.
• W4283013657 crossrefType "journal-article" @default.
• W4283013657 hasAuthorship W4283013657A5022732805 @default.
• W4283013657 hasAuthorship W4283013657A5050539684 @default.
• W4283013657 hasAuthorship W4283013657A5059021869 @default.
• W4283013657 hasAuthorship W4283013657A5071737735 @default.
• W4283013657 hasAuthorship W4283013657A5072440928 @default.
• W4283013657 hasAuthorship W4283013657A5083366771 @default.
• W4283013657 hasBestOaLocation W42830136571 @default.
• W4283013657 hasConcept C101738243 @default.
• W4283013657 hasConcept C108583219 @default.
• W4283013657 hasConcept C119857082 @default.
• W4283013657 hasConcept C121332964 @default.
• W4283013657 hasConcept C138885662 @default.
• W4283013657 hasConcept C153180895 @default.
• W4283013657 hasConcept C154945302 @default.
• W4283013657 hasConcept C17744445 @default.
• W4283013657 hasConcept C190470478 @default.
• W4283013657 hasConcept C199360897 @default.
• W4283013657 hasConcept C199539241 @default.
• W4283013657 hasConcept C24890656 @default.
• W4283013657 hasConcept C2776359362 @default.
• W4283013657 hasConcept C2778355321 @default.
• W4283013657 hasConcept C2779304628 @default.
• W4283013657 hasConcept C2780297707 @default.
• W4283013657 hasConcept C31972630 @default.
• W4283013657 hasConcept C33923547 @default.
• W4283013657 hasConcept C37914503 @default.
• W4283013657 hasConcept C41008148 @default.
• W4283013657 hasConcept C41895202 @default.
• W4283013657 hasConcept C59404180 @default.
• W4283013657 hasConcept C90559484 @default.
• W4283013657 hasConcept C94625758 @default.
• W4283013657 hasConceptScore W4283013657C101738243 @default.
• W4283013657 hasConceptScore W4283013657C108583219 @default.
• W4283013657 hasConceptScore W4283013657C119857082 @default.
• W4283013657 hasConceptScore W4283013657C121332964 @default.
• W4283013657 hasConceptScore W4283013657C138885662 @default.
• W4283013657 hasConceptScore W4283013657C153180895 @default.
• W4283013657 hasConceptScore W4283013657C154945302 @default.
• W4283013657 hasConceptScore W4283013657C17744445 @default.
• W4283013657 hasConceptScore W4283013657C190470478 @default.
• W4283013657 hasConceptScore W4283013657C199360897 @default.
• W4283013657 hasConceptScore W4283013657C199539241 @default.
• W4283013657 hasConceptScore W4283013657C24890656 @default.
• W4283013657 hasConceptScore W4283013657C2776359362 @default.
• W4283013657 hasConceptScore W4283013657C2778355321 @default.
• W4283013657 hasConceptScore W4283013657C2779304628 @default.
• W4283013657 hasConceptScore W4283013657C2780297707 @default.
• W4283013657 hasConceptScore W4283013657C31972630 @default.
• W4283013657 hasConceptScore W4283013657C33923547 @default.

• next