Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226103624> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4226103624 abstract "The quality of face images significantly influences the performance of underlying face recognition algorithms. Face image quality assessment (FIQA) estimates the utility of the captured image in achieving reliable and accurate recognition performance. In this work, we propose a novel learning paradigm that learns internal network observations during the training process. Based on that, our proposed CR-FIQA uses this paradigm to estimate the face image quality of a sample by predicting its relative classifiability. This classifiability is measured based on the allocation of the training sample feature representation in angular space with respect to its class center and the nearest negative class center. We experimentally illustrate the correlation between the face image quality and the sample relative classifiability. As such property is only observable for the training dataset, we propose to learn this property from the training dataset and utilize it to predict the quality measure on unseen samples. This training is performed simultaneously while optimizing the class centers by an angular margin penalty-based softmax loss used for face recognition model training. Through extensive evaluation experiments on eight benchmarks and four face recognition models, we demonstrate the superiority of our proposed CR-FIQA over state-of-the-art (SOTA) FIQA algorithms." @default.
- W4226103624 created "2022-05-05" @default.
- W4226103624 creator A5001243903 @default.
- W4226103624 creator A5028035125 @default.
- W4226103624 creator A5047906003 @default.
- W4226103624 creator A5059766088 @default.
- W4226103624 creator A5066185307 @default.
- W4226103624 date "2021-12-13" @default.
- W4226103624 modified "2023-09-29" @default.
- W4226103624 title "CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability" @default.
- W4226103624 hasPublicationYear "2021" @default.
- W4226103624 type Work @default.
- W4226103624 citedByCount "0" @default.
- W4226103624 crossrefType "posted-content" @default.
- W4226103624 hasAuthorship W4226103624A5001243903 @default.
- W4226103624 hasAuthorship W4226103624A5028035125 @default.
- W4226103624 hasAuthorship W4226103624A5047906003 @default.
- W4226103624 hasAuthorship W4226103624A5059766088 @default.
- W4226103624 hasAuthorship W4226103624A5066185307 @default.
- W4226103624 hasBestOaLocation W42261036241 @default.
- W4226103624 hasConcept C111472728 @default.
- W4226103624 hasConcept C115961682 @default.
- W4226103624 hasConcept C119857082 @default.
- W4226103624 hasConcept C138885662 @default.
- W4226103624 hasConcept C144024400 @default.
- W4226103624 hasConcept C153180895 @default.
- W4226103624 hasConcept C154945302 @default.
- W4226103624 hasConcept C185592680 @default.
- W4226103624 hasConcept C188441871 @default.
- W4226103624 hasConcept C189950617 @default.
- W4226103624 hasConcept C198531522 @default.
- W4226103624 hasConcept C2776401178 @default.
- W4226103624 hasConcept C2777212361 @default.
- W4226103624 hasConcept C2779304628 @default.
- W4226103624 hasConcept C2779530757 @default.
- W4226103624 hasConcept C31510193 @default.
- W4226103624 hasConcept C36289849 @default.
- W4226103624 hasConcept C41008148 @default.
- W4226103624 hasConcept C41895202 @default.
- W4226103624 hasConcept C43617362 @default.
- W4226103624 hasConcept C50644808 @default.
- W4226103624 hasConcept C52622490 @default.
- W4226103624 hasConcept C55020928 @default.
- W4226103624 hasConcept C774472 @default.
- W4226103624 hasConceptScore W4226103624C111472728 @default.
- W4226103624 hasConceptScore W4226103624C115961682 @default.
- W4226103624 hasConceptScore W4226103624C119857082 @default.
- W4226103624 hasConceptScore W4226103624C138885662 @default.
- W4226103624 hasConceptScore W4226103624C144024400 @default.
- W4226103624 hasConceptScore W4226103624C153180895 @default.
- W4226103624 hasConceptScore W4226103624C154945302 @default.
- W4226103624 hasConceptScore W4226103624C185592680 @default.
- W4226103624 hasConceptScore W4226103624C188441871 @default.
- W4226103624 hasConceptScore W4226103624C189950617 @default.
- W4226103624 hasConceptScore W4226103624C198531522 @default.
- W4226103624 hasConceptScore W4226103624C2776401178 @default.
- W4226103624 hasConceptScore W4226103624C2777212361 @default.
- W4226103624 hasConceptScore W4226103624C2779304628 @default.
- W4226103624 hasConceptScore W4226103624C2779530757 @default.
- W4226103624 hasConceptScore W4226103624C31510193 @default.
- W4226103624 hasConceptScore W4226103624C36289849 @default.
- W4226103624 hasConceptScore W4226103624C41008148 @default.
- W4226103624 hasConceptScore W4226103624C41895202 @default.
- W4226103624 hasConceptScore W4226103624C43617362 @default.
- W4226103624 hasConceptScore W4226103624C50644808 @default.
- W4226103624 hasConceptScore W4226103624C52622490 @default.
- W4226103624 hasConceptScore W4226103624C55020928 @default.
- W4226103624 hasConceptScore W4226103624C774472 @default.
- W4226103624 hasLocation W42261036241 @default.
- W4226103624 hasOpenAccess W4226103624 @default.
- W4226103624 hasPrimaryLocation W42261036241 @default.
- W4226103624 hasRelatedWork W13241864 @default.
- W4226103624 hasRelatedWork W1383942 @default.
- W4226103624 hasRelatedWork W14124867 @default.
- W4226103624 hasRelatedWork W14226645 @default.
- W4226103624 hasRelatedWork W1537934 @default.
- W4226103624 hasRelatedWork W247179 @default.
- W4226103624 hasRelatedWork W4789659 @default.
- W4226103624 hasRelatedWork W8232168 @default.
- W4226103624 hasRelatedWork W9474471 @default.
- W4226103624 hasRelatedWork W9940185 @default.
- W4226103624 isParatext "false" @default.
- W4226103624 isRetracted "false" @default.
- W4226103624 workType "article" @default.