Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945542907> ?p ?o ?g. }
- W2945542907 endingPage "2761" @default.
- W2945542907 startingPage "2750" @default.
- W2945542907 abstract "We present a deep learning-based method for removing makeup effects (de-makeup) in a face image. This problem poses a major challenge due to obscuring of the underlying facial features by cosmetics, which is very important in multimedia applications in the field of security, entertainment, and social networking. To address this task, we propose the bidirectional tunable de-makeup network (BTD-Net), which jointly learns the makeup process to aid in learning the de-makeup process. For tractable learning of the makeup process, which is a one-to-many mapping determined by the cosmetics that are applied, we introduce a latent variable that reflects the makeup style. This latent variable is extracted in the de-makeup process and used as a condition on the makeup process to constrain the one-to-many mapping to a specific solution. Through extensive experiments, our proposed BTD-Net is found to surpass the state-of-art techniques in estimating realistic non-makeup faces that correspond to the input makeup images. We additionally show that applications such as tuning the amount of makeup can be enhanced through the use of this method." @default.
- W2945542907 created "2019-05-29" @default.
- W2945542907 creator A5025114648 @default.
- W2945542907 creator A5032447166 @default.
- W2945542907 creator A5035689268 @default.
- W2945542907 creator A5050527785 @default.
- W2945542907 creator A5064912514 @default.
- W2945542907 date "2019-11-01" @default.
- W2945542907 modified "2023-10-16" @default.
- W2945542907 title "Makeup Removal via Bidirectional Tunable De-Makeup Network" @default.
- W2945542907 cites W1560538124 @default.
- W2945542907 cites W1868962909 @default.
- W2945542907 cites W1916003155 @default.
- W2945542907 cites W1916406603 @default.
- W2945542907 cites W1951319388 @default.
- W2945542907 cites W1976700763 @default.
- W2945542907 cites W1978370894 @default.
- W2945542907 cites W1987474052 @default.
- W2945542907 cites W2031365440 @default.
- W2945542907 cites W2056566827 @default.
- W2945542907 cites W2058191200 @default.
- W2945542907 cites W2068077579 @default.
- W2945542907 cites W2127470554 @default.
- W2945542907 cites W2136995369 @default.
- W2945542907 cites W2138251656 @default.
- W2945542907 cites W2194775991 @default.
- W2945542907 cites W2331128040 @default.
- W2945542907 cites W2469547219 @default.
- W2945542907 cites W2475287302 @default.
- W2945542907 cites W2552691119 @default.
- W2945542907 cites W2579578355 @default.
- W2945542907 cites W2587706859 @default.
- W2945542907 cites W2604721644 @default.
- W2945542907 cites W2611605760 @default.
- W2945542907 cites W2618116290 @default.
- W2945542907 cites W2776791908 @default.
- W2945542907 cites W2896240508 @default.
- W2945542907 cites W2962793481 @default.
- W2945542907 cites W2963073614 @default.
- W2945542907 cites W2963100452 @default.
- W2945542907 cites W2963393327 @default.
- W2945542907 cites W2963522749 @default.
- W2945542907 cites W2963917315 @default.
- W2945542907 cites W4233416708 @default.
- W2945542907 cites W4385229964 @default.
- W2945542907 doi "https://doi.org/10.1109/tmm.2019.2911457" @default.
- W2945542907 hasPublicationYear "2019" @default.
- W2945542907 type Work @default.
- W2945542907 sameAs 2945542907 @default.
- W2945542907 citedByCount "14" @default.
- W2945542907 countsByYear W29455429072018 @default.
- W2945542907 countsByYear W29455429072019 @default.
- W2945542907 countsByYear W29455429072020 @default.
- W2945542907 countsByYear W29455429072021 @default.
- W2945542907 countsByYear W29455429072022 @default.
- W2945542907 countsByYear W29455429072023 @default.
- W2945542907 crossrefType "journal-article" @default.
- W2945542907 hasAuthorship W2945542907A5025114648 @default.
- W2945542907 hasAuthorship W2945542907A5032447166 @default.
- W2945542907 hasAuthorship W2945542907A5035689268 @default.
- W2945542907 hasAuthorship W2945542907A5050527785 @default.
- W2945542907 hasAuthorship W2945542907A5064912514 @default.
- W2945542907 hasConcept C108583219 @default.
- W2945542907 hasConcept C111919701 @default.
- W2945542907 hasConcept C119857082 @default.
- W2945542907 hasConcept C134306372 @default.
- W2945542907 hasConcept C142724271 @default.
- W2945542907 hasConcept C144024400 @default.
- W2945542907 hasConcept C154945302 @default.
- W2945542907 hasConcept C162324750 @default.
- W2945542907 hasConcept C182365436 @default.
- W2945542907 hasConcept C187736073 @default.
- W2945542907 hasConcept C202444582 @default.
- W2945542907 hasConcept C2779304628 @default.
- W2945542907 hasConcept C2779717098 @default.
- W2945542907 hasConcept C2780451532 @default.
- W2945542907 hasConcept C31972630 @default.
- W2945542907 hasConcept C33923547 @default.
- W2945542907 hasConcept C36289849 @default.
- W2945542907 hasConcept C41008148 @default.
- W2945542907 hasConcept C51167844 @default.
- W2945542907 hasConcept C71924100 @default.
- W2945542907 hasConcept C9652623 @default.
- W2945542907 hasConcept C98045186 @default.
- W2945542907 hasConceptScore W2945542907C108583219 @default.
- W2945542907 hasConceptScore W2945542907C111919701 @default.
- W2945542907 hasConceptScore W2945542907C119857082 @default.
- W2945542907 hasConceptScore W2945542907C134306372 @default.
- W2945542907 hasConceptScore W2945542907C142724271 @default.
- W2945542907 hasConceptScore W2945542907C144024400 @default.
- W2945542907 hasConceptScore W2945542907C154945302 @default.
- W2945542907 hasConceptScore W2945542907C162324750 @default.
- W2945542907 hasConceptScore W2945542907C182365436 @default.
- W2945542907 hasConceptScore W2945542907C187736073 @default.
- W2945542907 hasConceptScore W2945542907C202444582 @default.
- W2945542907 hasConceptScore W2945542907C2779304628 @default.
- W2945542907 hasConceptScore W2945542907C2779717098 @default.
- W2945542907 hasConceptScore W2945542907C2780451532 @default.