Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128958304> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3128958304 abstract "Knowing how much to trust a prediction is important for many critical applications. We describe two simple approaches to estimate uncertainty in regression prediction tasks and compare their performance and complexity against popular approaches. We operationalize uncertainty in regression as the absolute error between a model’s prediction and the ground truth. Our two proposed approaches use a secondary model to predict the uncertainty of a primary predictive model. Our first approach leverages the assumption that similar observations are likely to have similar uncertainty and predicts uncertainty with a non-parametric method. Our second approach trains a secondary model to directly predict the uncertainty of the primary predictive model. Both approaches outperform other established uncertainty estimation approaches on the MNIST, DISFA, and BP4D+datasets. Furthermore, we observe that approaches that directly predict the uncertainty generally perform better than approaches that indirectly estimate uncertainty." @default.
- W3128958304 created "2021-02-15" @default.
- W3128958304 creator A5017680583 @default.
- W3128958304 creator A5081398601 @default.
- W3128958304 date "2020-11-01" @default.
- W3128958304 modified "2023-10-18" @default.
- W3128958304 title "Simple and Effective Approaches for Uncertainty Prediction in Facial Action Unit Intensity Regression" @default.
- W3128958304 cites W1594344279 @default.
- W3128958304 cites W2010546252 @default.
- W3128958304 cites W2045472600 @default.
- W3128958304 cites W2163517193 @default.
- W3128958304 cites W2470957930 @default.
- W3128958304 cites W2560185635 @default.
- W3128958304 cites W2594573597 @default.
- W3128958304 cites W2807126412 @default.
- W3128958304 cites W2899682268 @default.
- W3128958304 doi "https://doi.org/10.1109/fg47880.2020.00045" @default.
- W3128958304 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7935373" @default.
- W3128958304 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33679265" @default.
- W3128958304 hasPublicationYear "2020" @default.
- W3128958304 type Work @default.
- W3128958304 sameAs 3128958304 @default.
- W3128958304 citedByCount "2" @default.
- W3128958304 countsByYear W31289583042021 @default.
- W3128958304 countsByYear W31289583042022 @default.
- W3128958304 crossrefType "proceedings-article" @default.
- W3128958304 hasAuthorship W3128958304A5017680583 @default.
- W3128958304 hasAuthorship W3128958304A5081398601 @default.
- W3128958304 hasBestOaLocation W31289583042 @default.
- W3128958304 hasConcept C105795698 @default.
- W3128958304 hasConcept C111472728 @default.
- W3128958304 hasConcept C119857082 @default.
- W3128958304 hasConcept C120665830 @default.
- W3128958304 hasConcept C121332964 @default.
- W3128958304 hasConcept C122637931 @default.
- W3128958304 hasConcept C138885662 @default.
- W3128958304 hasConcept C145420912 @default.
- W3128958304 hasConcept C149769383 @default.
- W3128958304 hasConcept C152877465 @default.
- W3128958304 hasConcept C153180895 @default.
- W3128958304 hasConcept C154945302 @default.
- W3128958304 hasConcept C2780586882 @default.
- W3128958304 hasConcept C2780791683 @default.
- W3128958304 hasConcept C33923547 @default.
- W3128958304 hasConcept C41008148 @default.
- W3128958304 hasConcept C62520636 @default.
- W3128958304 hasConcept C83546350 @default.
- W3128958304 hasConcept C93038891 @default.
- W3128958304 hasConceptScore W3128958304C105795698 @default.
- W3128958304 hasConceptScore W3128958304C111472728 @default.
- W3128958304 hasConceptScore W3128958304C119857082 @default.
- W3128958304 hasConceptScore W3128958304C120665830 @default.
- W3128958304 hasConceptScore W3128958304C121332964 @default.
- W3128958304 hasConceptScore W3128958304C122637931 @default.
- W3128958304 hasConceptScore W3128958304C138885662 @default.
- W3128958304 hasConceptScore W3128958304C145420912 @default.
- W3128958304 hasConceptScore W3128958304C149769383 @default.
- W3128958304 hasConceptScore W3128958304C152877465 @default.
- W3128958304 hasConceptScore W3128958304C153180895 @default.
- W3128958304 hasConceptScore W3128958304C154945302 @default.
- W3128958304 hasConceptScore W3128958304C2780586882 @default.
- W3128958304 hasConceptScore W3128958304C2780791683 @default.
- W3128958304 hasConceptScore W3128958304C33923547 @default.
- W3128958304 hasConceptScore W3128958304C41008148 @default.
- W3128958304 hasConceptScore W3128958304C62520636 @default.
- W3128958304 hasConceptScore W3128958304C83546350 @default.
- W3128958304 hasConceptScore W3128958304C93038891 @default.
- W3128958304 hasLocation W31289583041 @default.
- W3128958304 hasLocation W31289583042 @default.
- W3128958304 hasOpenAccess W3128958304 @default.
- W3128958304 hasPrimaryLocation W31289583041 @default.
- W3128958304 hasRelatedWork W1858292687 @default.
- W3128958304 hasRelatedWork W2018697919 @default.
- W3128958304 hasRelatedWork W2059948469 @default.
- W3128958304 hasRelatedWork W2093259327 @default.
- W3128958304 hasRelatedWork W2273635254 @default.
- W3128958304 hasRelatedWork W2359745278 @default.
- W3128958304 hasRelatedWork W2464815299 @default.
- W3128958304 hasRelatedWork W3042029886 @default.
- W3128958304 hasRelatedWork W4249094282 @default.
- W3128958304 hasRelatedWork W2184922845 @default.
- W3128958304 isParatext "false" @default.
- W3128958304 isRetracted "false" @default.
- W3128958304 magId "3128958304" @default.
- W3128958304 workType "article" @default.