Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207929382> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3207929382 endingPage "116004" @default.
- W3207929382 startingPage "116004" @default.
- W3207929382 abstract "Semantic segmentation of images by Fully Convolutional Neural Networks (FCN) has gained increased attention in recent years as FCNs greatly outperform traditional segmentation algorithms. In this paper we propose using Ellipse Fit Error as a shape prior regularization term that can be added to a pixel-wise loss function, e.g., binary cross entropy, to train a CNN for pupil segmentation. We evaluate the performance of the proposed method by training a lightweight UNet architecture, and use three widely used real-world datasets for pupil center estimation, i.e., ExCuSe, ElSe, and Labeled Pupils in the Wild (LPW), containing a total of ∼230.000 images for performance evaluation. Experimental results show that the proposed method gives the best-known pupil detection rates for all datasets." @default.
- W3207929382 created "2021-10-25" @default.
- W3207929382 creator A5047703190 @default.
- W3207929382 creator A5048504975 @default.
- W3207929382 creator A5070786755 @default.
- W3207929382 date "2022-02-01" @default.
- W3207929382 modified "2023-10-01" @default.
- W3207929382 title "Accurate CNN-based pupil segmentation with an ellipse fit error regularization term" @default.
- W3207929382 cites W1979567358 @default.
- W3207929382 cites W2000789130 @default.
- W3207929382 cites W2016222375 @default.
- W3207929382 cites W2085261163 @default.
- W3207929382 cites W2145023731 @default.
- W3207929382 cites W2150497272 @default.
- W3207929382 cites W2290202588 @default.
- W3207929382 cites W2409999048 @default.
- W3207929382 cites W2549090644 @default.
- W3207929382 cites W2586957729 @default.
- W3207929382 cites W2608277432 @default.
- W3207929382 cites W2737383589 @default.
- W3207929382 cites W2772878363 @default.
- W3207929382 cites W2963881378 @default.
- W3207929382 cites W2966434031 @default.
- W3207929382 cites W3014325892 @default.
- W3207929382 cites W3144221682 @default.
- W3207929382 cites W3153388040 @default.
- W3207929382 doi "https://doi.org/10.1016/j.eswa.2021.116004" @default.
- W3207929382 hasPublicationYear "2022" @default.
- W3207929382 type Work @default.
- W3207929382 sameAs 3207929382 @default.
- W3207929382 citedByCount "4" @default.
- W3207929382 countsByYear W32079293822022 @default.
- W3207929382 countsByYear W32079293822023 @default.
- W3207929382 crossrefType "journal-article" @default.
- W3207929382 hasAuthorship W3207929382A5047703190 @default.
- W3207929382 hasAuthorship W3207929382A5048504975 @default.
- W3207929382 hasAuthorship W3207929382A5070786755 @default.
- W3207929382 hasConcept C121332964 @default.
- W3207929382 hasConcept C153180895 @default.
- W3207929382 hasConcept C154945302 @default.
- W3207929382 hasConcept C160633673 @default.
- W3207929382 hasConcept C167981619 @default.
- W3207929382 hasConcept C169760540 @default.
- W3207929382 hasConcept C2524010 @default.
- W3207929382 hasConcept C2776135515 @default.
- W3207929382 hasConcept C2777394604 @default.
- W3207929382 hasConcept C31972630 @default.
- W3207929382 hasConcept C33923547 @default.
- W3207929382 hasConcept C41008148 @default.
- W3207929382 hasConcept C48372109 @default.
- W3207929382 hasConcept C61797465 @default.
- W3207929382 hasConcept C62520636 @default.
- W3207929382 hasConcept C74261601 @default.
- W3207929382 hasConcept C81363708 @default.
- W3207929382 hasConcept C86803240 @default.
- W3207929382 hasConcept C89600930 @default.
- W3207929382 hasConcept C94375191 @default.
- W3207929382 hasConceptScore W3207929382C121332964 @default.
- W3207929382 hasConceptScore W3207929382C153180895 @default.
- W3207929382 hasConceptScore W3207929382C154945302 @default.
- W3207929382 hasConceptScore W3207929382C160633673 @default.
- W3207929382 hasConceptScore W3207929382C167981619 @default.
- W3207929382 hasConceptScore W3207929382C169760540 @default.
- W3207929382 hasConceptScore W3207929382C2524010 @default.
- W3207929382 hasConceptScore W3207929382C2776135515 @default.
- W3207929382 hasConceptScore W3207929382C2777394604 @default.
- W3207929382 hasConceptScore W3207929382C31972630 @default.
- W3207929382 hasConceptScore W3207929382C33923547 @default.
- W3207929382 hasConceptScore W3207929382C41008148 @default.
- W3207929382 hasConceptScore W3207929382C48372109 @default.
- W3207929382 hasConceptScore W3207929382C61797465 @default.
- W3207929382 hasConceptScore W3207929382C62520636 @default.
- W3207929382 hasConceptScore W3207929382C74261601 @default.
- W3207929382 hasConceptScore W3207929382C81363708 @default.
- W3207929382 hasConceptScore W3207929382C86803240 @default.
- W3207929382 hasConceptScore W3207929382C89600930 @default.
- W3207929382 hasConceptScore W3207929382C94375191 @default.
- W3207929382 hasLocation W32079293821 @default.
- W3207929382 hasOpenAccess W3207929382 @default.
- W3207929382 hasPrimaryLocation W32079293821 @default.
- W3207929382 hasRelatedWork W1669643531 @default.
- W3207929382 hasRelatedWork W2005437358 @default.
- W3207929382 hasRelatedWork W2008656436 @default.
- W3207929382 hasRelatedWork W2023558673 @default.
- W3207929382 hasRelatedWork W2072834229 @default.
- W3207929382 hasRelatedWork W2134924024 @default.
- W3207929382 hasRelatedWork W2337415362 @default.
- W3207929382 hasRelatedWork W2517104666 @default.
- W3207929382 hasRelatedWork W2532331858 @default.
- W3207929382 hasRelatedWork W2791121587 @default.
- W3207929382 hasVolume "188" @default.
- W3207929382 isParatext "false" @default.
- W3207929382 isRetracted "false" @default.
- W3207929382 magId "3207929382" @default.
- W3207929382 workType "article" @default.