Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284977237> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4284977237 endingPage "254" @default.
- W4284977237 startingPage "246" @default.
- W4284977237 abstract "Convolutional Neural Networks have achieved state-of-the-art performance in image classification. Their lack of ability to recognise the spatial relationship between features, however, leads to misclassification of the variants of the same image. Capsule Networks were introduced to address this issue by incorporating the spatial information of image features into neural networks. In this paper, we are interested in showcasing the digit recognition task on CAPTCHA images, widely considered a challenge for computers in relation to human capabilities. Our intention is to provide a rigorous empirical regime in which we can compare the competitive performance of Capsule Networks against the Convolutional Neural Networks. Indeed since CAPTCHA distorts images, by adjusting the spatial positioning of features, we aim to demonstrate the advantages and limitations of Capsule Networks architecture. We train the Capsule Networks with Dynamic Routing version and the convolutional-neural-network-based deep-CAPTCHA baseline model to predict the digit sequences on numerical CAPTCHAs, investigate the performance results and propose two improvements to the Capsule Networks model." @default.
- W4284977237 created "2022-07-10" @default.
- W4284977237 creator A5002932153 @default.
- W4284977237 creator A5016649653 @default.
- W4284977237 creator A5079430739 @default.
- W4284977237 date "2022-10-01" @default.
- W4284977237 modified "2023-09-27" @default.
- W4284977237 title "Breaking CAPTCHA with Capsule Networks" @default.
- W4284977237 cites W1869383794 @default.
- W4284977237 cites W2072410439 @default.
- W4284977237 cites W2618530766 @default.
- W4284977237 cites W2761974878 @default.
- W4284977237 cites W2895526696 @default.
- W4284977237 cites W2985145919 @default.
- W4284977237 cites W3096357229 @default.
- W4284977237 cites W3102100346 @default.
- W4284977237 cites W3154170615 @default.
- W4284977237 cites W3158436118 @default.
- W4284977237 cites W3178621454 @default.
- W4284977237 cites W3213678982 @default.
- W4284977237 cites W4206604443 @default.
- W4284977237 doi "https://doi.org/10.1016/j.neunet.2022.06.041" @default.
- W4284977237 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35908374" @default.
- W4284977237 hasPublicationYear "2022" @default.
- W4284977237 type Work @default.
- W4284977237 citedByCount "0" @default.
- W4284977237 crossrefType "journal-article" @default.
- W4284977237 hasAuthorship W4284977237A5002932153 @default.
- W4284977237 hasAuthorship W4284977237A5016649653 @default.
- W4284977237 hasAuthorship W4284977237A5079430739 @default.
- W4284977237 hasBestOaLocation W42849772372 @default.
- W4284977237 hasConcept C108583219 @default.
- W4284977237 hasConcept C115961682 @default.
- W4284977237 hasConcept C119857082 @default.
- W4284977237 hasConcept C153180895 @default.
- W4284977237 hasConcept C154945302 @default.
- W4284977237 hasConcept C162324750 @default.
- W4284977237 hasConcept C163339463 @default.
- W4284977237 hasConcept C187736073 @default.
- W4284977237 hasConcept C2780451532 @default.
- W4284977237 hasConcept C41008148 @default.
- W4284977237 hasConcept C50644808 @default.
- W4284977237 hasConcept C81363708 @default.
- W4284977237 hasConceptScore W4284977237C108583219 @default.
- W4284977237 hasConceptScore W4284977237C115961682 @default.
- W4284977237 hasConceptScore W4284977237C119857082 @default.
- W4284977237 hasConceptScore W4284977237C153180895 @default.
- W4284977237 hasConceptScore W4284977237C154945302 @default.
- W4284977237 hasConceptScore W4284977237C162324750 @default.
- W4284977237 hasConceptScore W4284977237C163339463 @default.
- W4284977237 hasConceptScore W4284977237C187736073 @default.
- W4284977237 hasConceptScore W4284977237C2780451532 @default.
- W4284977237 hasConceptScore W4284977237C41008148 @default.
- W4284977237 hasConceptScore W4284977237C50644808 @default.
- W4284977237 hasConceptScore W4284977237C81363708 @default.
- W4284977237 hasFunder F4320314731 @default.
- W4284977237 hasFunder F4320320006 @default.
- W4284977237 hasFunder F4320320332 @default.
- W4284977237 hasFunder F4320334627 @default.
- W4284977237 hasLocation W42849772371 @default.
- W4284977237 hasLocation W42849772372 @default.
- W4284977237 hasLocation W42849772373 @default.
- W4284977237 hasOpenAccess W4284977237 @default.
- W4284977237 hasPrimaryLocation W42849772371 @default.
- W4284977237 hasRelatedWork W2337926734 @default.
- W4284977237 hasRelatedWork W2732542196 @default.
- W4284977237 hasRelatedWork W2738221750 @default.
- W4284977237 hasRelatedWork W2963958939 @default.
- W4284977237 hasRelatedWork W3021430260 @default.
- W4284977237 hasRelatedWork W4214561993 @default.
- W4284977237 hasRelatedWork W4311257506 @default.
- W4284977237 hasRelatedWork W4319994054 @default.
- W4284977237 hasRelatedWork W4320802194 @default.
- W4284977237 hasRelatedWork W564581980 @default.
- W4284977237 hasVolume "154" @default.
- W4284977237 isParatext "false" @default.
- W4284977237 isRetracted "false" @default.
- W4284977237 workType "article" @default.