Matches in SemOpenAlex for { <https://semopenalex.org/work/W3118366978> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3118366978 abstract "Computer Vision practitioners must thoroughly understand their model's performance, but conditional evaluation is complex and error-prone. In biometric verification, model performance over continuous covariates - known, real-number attributes of images that affect performance - is particularly challenging to study. We develop a generative model of the match and non-match score distributions over continuous covariates and perform inference with modern Bayesian methods. We use mixture models to capture arbitrary distributions and local basis functions to capture non-linear, multivariate trends. Three experiments demonstrate the accuracy and effectiveness of our approach. First, we study the relationship between age and face verification performance and find previous methods may overstate performance and confidence. Second, we study preprocessing for CNNs and find a highly non-linear, multivariate surface of model performance. Our method is accurate and data efficient when evaluated against previous synthetic methods. Third, we demonstrate the novel application of our method to pedestrian tracking and calculate variable thresholds and expected performance while controlling for multiple covariates." @default.
- W3118366978 created "2021-01-18" @default.
- W3118366978 creator A5026106240 @default.
- W3118366978 creator A5027477070 @default.
- W3118366978 creator A5051029455 @default.
- W3118366978 creator A5091513740 @default.
- W3118366978 date "2020-09-28" @default.
- W3118366978 modified "2023-09-26" @default.
- W3118366978 title "Modeling Score Distributions and Continuous Covariates: A Bayesian Approach" @default.
- W3118366978 cites W1782590233 @default.
- W3118366978 cites W1978642336 @default.
- W3118366978 cites W1981291049 @default.
- W3118366978 cites W2035830871 @default.
- W3118366978 cites W2096838591 @default.
- W3118366978 cites W2101123607 @default.
- W3118366978 cites W2137385871 @default.
- W3118366978 cites W2137837190 @default.
- W3118366978 cites W2552164092 @default.
- W3118366978 cites W2572045081 @default.
- W3118366978 cites W2603203130 @default.
- W3118366978 cites W2755255259 @default.
- W3118366978 cites W2771583656 @default.
- W3118366978 cites W2912376035 @default.
- W3118366978 cites W2912406707 @default.
- W3118366978 cites W2949386440 @default.
- W3118366978 cites W2962997291 @default.
- W3118366978 cites W2963544815 @default.
- W3118366978 cites W2963767194 @default.
- W3118366978 cites W2963839617 @default.
- W3118366978 cites W2964321317 @default.
- W3118366978 cites W2966535964 @default.
- W3118366978 cites W2970971581 @default.
- W3118366978 cites W2976315811 @default.
- W3118366978 cites W2984145721 @default.
- W3118366978 cites W3010400237 @default.
- W3118366978 cites W3013086920 @default.
- W3118366978 doi "https://doi.org/10.1109/ijcb48548.2020.9304938" @default.
- W3118366978 hasPublicationYear "2020" @default.
- W3118366978 type Work @default.
- W3118366978 sameAs 3118366978 @default.
- W3118366978 citedByCount "1" @default.
- W3118366978 countsByYear W31183669782021 @default.
- W3118366978 crossrefType "proceedings-article" @default.
- W3118366978 hasAuthorship W3118366978A5026106240 @default.
- W3118366978 hasAuthorship W3118366978A5027477070 @default.
- W3118366978 hasAuthorship W3118366978A5051029455 @default.
- W3118366978 hasAuthorship W3118366978A5091513740 @default.
- W3118366978 hasBestOaLocation W31183669782 @default.
- W3118366978 hasConcept C107673813 @default.
- W3118366978 hasConcept C119043178 @default.
- W3118366978 hasConcept C119857082 @default.
- W3118366978 hasConcept C124101348 @default.
- W3118366978 hasConcept C153180895 @default.
- W3118366978 hasConcept C154945302 @default.
- W3118366978 hasConcept C161584116 @default.
- W3118366978 hasConcept C184297639 @default.
- W3118366978 hasConcept C2776214188 @default.
- W3118366978 hasConcept C41008148 @default.
- W3118366978 hasConceptScore W3118366978C107673813 @default.
- W3118366978 hasConceptScore W3118366978C119043178 @default.
- W3118366978 hasConceptScore W3118366978C119857082 @default.
- W3118366978 hasConceptScore W3118366978C124101348 @default.
- W3118366978 hasConceptScore W3118366978C153180895 @default.
- W3118366978 hasConceptScore W3118366978C154945302 @default.
- W3118366978 hasConceptScore W3118366978C161584116 @default.
- W3118366978 hasConceptScore W3118366978C184297639 @default.
- W3118366978 hasConceptScore W3118366978C2776214188 @default.
- W3118366978 hasConceptScore W3118366978C41008148 @default.
- W3118366978 hasLocation W31183669781 @default.
- W3118366978 hasLocation W31183669782 @default.
- W3118366978 hasOpenAccess W3118366978 @default.
- W3118366978 hasPrimaryLocation W31183669781 @default.
- W3118366978 hasRelatedWork W2044158 @default.
- W3118366978 hasRelatedWork W2777878 @default.
- W3118366978 hasRelatedWork W4272086 @default.
- W3118366978 hasRelatedWork W4505823 @default.
- W3118366978 hasRelatedWork W695875 @default.
- W3118366978 hasRelatedWork W760780 @default.
- W3118366978 hasRelatedWork W8021486 @default.
- W3118366978 hasRelatedWork W9177359 @default.
- W3118366978 hasRelatedWork W9329549 @default.
- W3118366978 hasRelatedWork W722847 @default.
- W3118366978 isParatext "false" @default.
- W3118366978 isRetracted "false" @default.
- W3118366978 magId "3118366978" @default.
- W3118366978 workType "article" @default.