FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035376925> ?p ?o ?g. }

• W3035376925 abstract "Modeling data uncertainty is important for noisy images, but seldom explored for face recognition. The pioneer work, PFE, considers uncertainty by modeling each face image embedding as a Gaussian distribution. It is quite effective. However, it uses fixed feature (mean of the Gaussian) from an existing model. It only estimates the variance and relies on an ad-hoc and costly metric. Thus, it is not easy to use. It is unclear how uncertainty affects feature learning. This work applies data uncertainty learning to face recognition, such that the feature (mean) and uncertainty (variance) are learnt simultaneously, for the first time. Two learning methods are proposed. They are easy to use and outperform existing deterministic methods as well as PFE on challenging unconstrained scenarios. We also provide insightful analysis on how incorporating uncertainty estimation helps reducing the adverse effects of noisy samples and affects the feature learning." @default.
• W3035376925 created "2020-06-19" @default.
• W3035376925 creator A5018706097 @default.
• W3035376925 creator A5048152070 @default.
• W3035376925 creator A5055158787 @default.
• W3035376925 creator A5081897818 @default.
• W3035376925 date "2020-06-01" @default.
• W3035376925 modified "2023-10-10" @default.
• W3035376925 title "Data Uncertainty Learning in Face Recognition" @default.
• W3035376925 cites W1560021816 @default.
• W3035376925 cites W1950843348 @default.
• W3035376925 cites W1978904760 @default.
• W3035376925 cites W2019464758 @default.
• W3035376925 cites W2024922353 @default.
• W3035376925 cites W2029590430 @default.
• W3035376925 cites W2055825262 @default.
• W3035376925 cites W2111959010 @default.
• W3035376925 cites W2194775991 @default.
• W3035376925 cites W2404498690 @default.
• W3035376925 cites W2742903236 @default.
• W3035376925 cites W2752782242 @default.
• W3035376925 cites W2871667416 @default.
• W3035376925 cites W2913592748 @default.
• W3035376925 cites W2917234874 @default.
• W3035376925 cites W2962898354 @default.
• W3035376925 cites W2963460857 @default.
• W3035376925 cites W2963466847 @default.
• W3035376925 cites W2963671154 @default.
• W3035376925 cites W2963839617 @default.
• W3035376925 cites W2964054038 @default.
• W3035376925 cites W2964184826 @default.
• W3035376925 cites W2964198847 @default.
• W3035376925 cites W2967637014 @default.
• W3035376925 cites W2969985801 @default.
• W3035376925 cites W2978968642 @default.
• W3035376925 cites W2981958729 @default.
• W3035376925 cites W2984006054 @default.
• W3035376925 cites W3098691969 @default.
• W3035376925 cites W3098883884 @default.
• W3035376925 cites W3099206234 @default.
• W3035376925 cites W3103152812 @default.
• W3035376925 doi "https://doi.org/10.1109/cvpr42600.2020.00575" @default.
• W3035376925 hasPublicationYear "2020" @default.
• W3035376925 type Work @default.
• W3035376925 sameAs 3035376925 @default.
• W3035376925 citedByCount "133" @default.
• W3035376925 countsByYear W30353769252020 @default.
• W3035376925 countsByYear W30353769252021 @default.
• W3035376925 countsByYear W30353769252022 @default.
• W3035376925 countsByYear W30353769252023 @default.
• W3035376925 crossrefType "proceedings-article" @default.
• W3035376925 hasAuthorship W3035376925A5018706097 @default.
• W3035376925 hasAuthorship W3035376925A5048152070 @default.
• W3035376925 hasAuthorship W3035376925A5055158787 @default.
• W3035376925 hasAuthorship W3035376925A5081897818 @default.
• W3035376925 hasBestOaLocation W30353769252 @default.
• W3035376925 hasConcept C105795698 @default.
• W3035376925 hasConcept C119857082 @default.
• W3035376925 hasConcept C121332964 @default.
• W3035376925 hasConcept C121955636 @default.
• W3035376925 hasConcept C127413603 @default.
• W3035376925 hasConcept C138885662 @default.
• W3035376925 hasConcept C144024400 @default.
• W3035376925 hasConcept C144133560 @default.
• W3035376925 hasConcept C149441793 @default.
• W3035376925 hasConcept C153180895 @default.
• W3035376925 hasConcept C154945302 @default.
• W3035376925 hasConcept C163716315 @default.
• W3035376925 hasConcept C176217482 @default.
• W3035376925 hasConcept C196083921 @default.
• W3035376925 hasConcept C21547014 @default.
• W3035376925 hasConcept C2776401178 @default.
• W3035376925 hasConcept C2779304628 @default.
• W3035376925 hasConcept C31510193 @default.
• W3035376925 hasConcept C33923547 @default.
• W3035376925 hasConcept C36289849 @default.
• W3035376925 hasConcept C41008148 @default.
• W3035376925 hasConcept C41608201 @default.
• W3035376925 hasConcept C41895202 @default.
• W3035376925 hasConcept C61326573 @default.
• W3035376925 hasConcept C62520636 @default.
• W3035376925 hasConceptScore W3035376925C105795698 @default.
• W3035376925 hasConceptScore W3035376925C119857082 @default.
• W3035376925 hasConceptScore W3035376925C121332964 @default.
• W3035376925 hasConceptScore W3035376925C121955636 @default.
• W3035376925 hasConceptScore W3035376925C127413603 @default.
• W3035376925 hasConceptScore W3035376925C138885662 @default.
• W3035376925 hasConceptScore W3035376925C144024400 @default.
• W3035376925 hasConceptScore W3035376925C144133560 @default.
• W3035376925 hasConceptScore W3035376925C149441793 @default.
• W3035376925 hasConceptScore W3035376925C153180895 @default.
• W3035376925 hasConceptScore W3035376925C154945302 @default.
• W3035376925 hasConceptScore W3035376925C163716315 @default.
• W3035376925 hasConceptScore W3035376925C176217482 @default.
• W3035376925 hasConceptScore W3035376925C196083921 @default.
• W3035376925 hasConceptScore W3035376925C21547014 @default.
• W3035376925 hasConceptScore W3035376925C2776401178 @default.
• W3035376925 hasConceptScore W3035376925C2779304628 @default.
• W3035376925 hasConceptScore W3035376925C31510193 @default.
• W3035376925 hasConceptScore W3035376925C33923547 @default.

• next