Matches in SemOpenAlex for { <https://semopenalex.org/work/W3026168715> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3026168715 endingPage "127" @default.
- W3026168715 startingPage "127" @default.
- W3026168715 abstract "In this paper, we explore the effect of using different convolutional layers, batch normalization and the global average pooling layer upon a convolutional neural network (CNN) based gaze tracking system. A novel method is proposed to label the participant’s face images as gaze points retrieved from eye tracker while watching videos for building a training dataset that is closer to human visual behavior. The participants can swing their head freely; therefore, the most real and natural images can be obtained without too many restrictions. The labeled data are classified according to the coordinate of gaze and area of interest on the screen. Therefore, varied network architectures are applied to estimate and compare the effects including the number of convolutional layers, batch normalization (BN) and the global average pooling (GAP) layer instead of the fully connected layer. Three schemes, including the single eye image, double eyes image and facial image, with data augmentation are used to feed into neural network to train and evaluate the efficiency. The input image of the eye or face for an eye tracking system is mostly a small-sized image with relatively few features. The results show that BN and GAP are helpful in overcoming the problem to train models and in reducing the amount of network parameters. It is shown that the accuracy is significantly improved when using GAP and BN at the mean time. Overall, the face scheme has a highest accuracy of 0.883 when BN and GAP are used at the mean time. Additionally, comparing to the fully connected layer set to 512 cases, the number of parameters is reduced by less than 50% and the accuracy is improved by about 2%. A detection accuracy comparison of our model with the existing George and Routray methods shows that our proposed method achieves better prediction accuracy of more than 6%." @default.
- W3026168715 created "2020-05-29" @default.
- W3026168715 creator A5011095245 @default.
- W3026168715 creator A5018341980 @default.
- W3026168715 creator A5033006458 @default.
- W3026168715 creator A5045534654 @default.
- W3026168715 date "2020-05-19" @default.
- W3026168715 modified "2023-09-29" @default.
- W3026168715 title "The Effect of Different Deep Network Architectures upon CNN-Based Gaze Tracking" @default.
- W3026168715 cites W2052487768 @default.
- W3026168715 cites W2112796928 @default.
- W3026168715 cites W2114902384 @default.
- W3026168715 cites W2167020116 @default.
- W3026168715 cites W2492303557 @default.
- W3026168715 cites W2743391672 @default.
- W3026168715 cites W2912872939 @default.
- W3026168715 cites W2914496424 @default.
- W3026168715 cites W2960173979 @default.
- W3026168715 cites W2963304222 @default.
- W3026168715 doi "https://doi.org/10.3390/a13050127" @default.
- W3026168715 hasPublicationYear "2020" @default.
- W3026168715 type Work @default.
- W3026168715 sameAs 3026168715 @default.
- W3026168715 citedByCount "4" @default.
- W3026168715 countsByYear W30261687152021 @default.
- W3026168715 countsByYear W30261687152022 @default.
- W3026168715 countsByYear W30261687152023 @default.
- W3026168715 crossrefType "journal-article" @default.
- W3026168715 hasAuthorship W3026168715A5011095245 @default.
- W3026168715 hasAuthorship W3026168715A5018341980 @default.
- W3026168715 hasAuthorship W3026168715A5033006458 @default.
- W3026168715 hasAuthorship W3026168715A5045534654 @default.
- W3026168715 hasBestOaLocation W30261687151 @default.
- W3026168715 hasConcept C136886441 @default.
- W3026168715 hasConcept C144024400 @default.
- W3026168715 hasConcept C153180895 @default.
- W3026168715 hasConcept C154945302 @default.
- W3026168715 hasConcept C19165224 @default.
- W3026168715 hasConcept C2779304628 @default.
- W3026168715 hasConcept C2779916870 @default.
- W3026168715 hasConcept C31972630 @default.
- W3026168715 hasConcept C36289849 @default.
- W3026168715 hasConcept C41008148 @default.
- W3026168715 hasConcept C56461940 @default.
- W3026168715 hasConcept C70437156 @default.
- W3026168715 hasConcept C81363708 @default.
- W3026168715 hasConceptScore W3026168715C136886441 @default.
- W3026168715 hasConceptScore W3026168715C144024400 @default.
- W3026168715 hasConceptScore W3026168715C153180895 @default.
- W3026168715 hasConceptScore W3026168715C154945302 @default.
- W3026168715 hasConceptScore W3026168715C19165224 @default.
- W3026168715 hasConceptScore W3026168715C2779304628 @default.
- W3026168715 hasConceptScore W3026168715C2779916870 @default.
- W3026168715 hasConceptScore W3026168715C31972630 @default.
- W3026168715 hasConceptScore W3026168715C36289849 @default.
- W3026168715 hasConceptScore W3026168715C41008148 @default.
- W3026168715 hasConceptScore W3026168715C56461940 @default.
- W3026168715 hasConceptScore W3026168715C70437156 @default.
- W3026168715 hasConceptScore W3026168715C81363708 @default.
- W3026168715 hasIssue "5" @default.
- W3026168715 hasLocation W30261687151 @default.
- W3026168715 hasLocation W30261687152 @default.
- W3026168715 hasOpenAccess W3026168715 @default.
- W3026168715 hasPrimaryLocation W30261687151 @default.
- W3026168715 hasRelatedWork W1561602432 @default.
- W3026168715 hasRelatedWork W1589443630 @default.
- W3026168715 hasRelatedWork W1999328396 @default.
- W3026168715 hasRelatedWork W2113986142 @default.
- W3026168715 hasRelatedWork W2127677160 @default.
- W3026168715 hasRelatedWork W2148584227 @default.
- W3026168715 hasRelatedWork W2168991662 @default.
- W3026168715 hasRelatedWork W2385108104 @default.
- W3026168715 hasRelatedWork W2769824675 @default.
- W3026168715 hasRelatedWork W2183271128 @default.
- W3026168715 hasVolume "13" @default.
- W3026168715 isParatext "false" @default.
- W3026168715 isRetracted "false" @default.
- W3026168715 magId "3026168715" @default.
- W3026168715 workType "article" @default.