Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893776197> ?p ?o ?g. }
- W2893776197 endingPage "74" @default.
- W2893776197 startingPage "64" @default.
- W2893776197 abstract "There are two types of information in each handwritten word image: explicit information which can be easily read or derived directly, such as lexical content or word length, and implicit attributes such as the author's identity. Whether features learned by a neural network for one task can be used for another task remains an open question. In this paper, we present a deep adaptive learning method for writer identification based on single-word images using multi-task learning. An auxiliary task is added to the training process to enforce the emergence of reusable features. Our proposed method transfers the benefits of the learned features of a convolutional neural network from an auxiliary task such as explicit content recognition to the main task of writer identification in a single procedure. Specifically, we propose a new adaptive convolutional layer to exploit the learned deep features. A multi-task neural network with one or several adaptive convolutional layers is trained end-to-end, to exploit robust generic features for a specific main task, i.e., writer identification. Three auxiliary tasks, corresponding to three explicit attributes of handwritten word images (lexical content, word length and character attributes), are evaluated. Experimental results on two benchmark datasets show that the proposed deep adaptive learning method can improve the performance of writer identification based on single-word images, compared to non-adaptive and simple linear-adaptive approaches." @default.
- W2893776197 created "2018-10-05" @default.
- W2893776197 creator A5028858025 @default.
- W2893776197 creator A5064975660 @default.
- W2893776197 date "2019-04-01" @default.
- W2893776197 modified "2023-10-04" @default.
- W2893776197 title "Deep adaptive learning for writer identification based on single handwritten word images" @default.
- W2893776197 cites W1966917421 @default.
- W2893776197 cites W1993487275 @default.
- W2893776197 cites W1997828165 @default.
- W2893776197 cites W2000423522 @default.
- W2893776197 cites W2036889485 @default.
- W2893776197 cites W2050088446 @default.
- W2893776197 cites W2053317383 @default.
- W2893776197 cites W2074812954 @default.
- W2893776197 cites W2076107430 @default.
- W2893776197 cites W2090985198 @default.
- W2893776197 cites W2120987116 @default.
- W2893776197 cites W2124090627 @default.
- W2893776197 cites W2130451799 @default.
- W2893776197 cites W2130478883 @default.
- W2893776197 cites W2131991463 @default.
- W2893776197 cites W2151103935 @default.
- W2893776197 cites W2152446828 @default.
- W2893776197 cites W2152928267 @default.
- W2893776197 cites W2154705238 @default.
- W2893776197 cites W2170737087 @default.
- W2893776197 cites W2344340558 @default.
- W2893776197 cites W2405472697 @default.
- W2893776197 cites W2522010881 @default.
- W2893776197 cites W2524608787 @default.
- W2893776197 cites W2527189503 @default.
- W2893776197 cites W2529897829 @default.
- W2893776197 cites W2618530766 @default.
- W2893776197 cites W2962779710 @default.
- W2893776197 cites W601793257 @default.
- W2893776197 doi "https://doi.org/10.1016/j.patcog.2018.11.003" @default.
- W2893776197 hasPublicationYear "2019" @default.
- W2893776197 type Work @default.
- W2893776197 sameAs 2893776197 @default.
- W2893776197 citedByCount "53" @default.
- W2893776197 countsByYear W28937761972019 @default.
- W2893776197 countsByYear W28937761972020 @default.
- W2893776197 countsByYear W28937761972021 @default.
- W2893776197 countsByYear W28937761972022 @default.
- W2893776197 countsByYear W28937761972023 @default.
- W2893776197 crossrefType "journal-article" @default.
- W2893776197 hasAuthorship W2893776197A5028858025 @default.
- W2893776197 hasAuthorship W2893776197A5064975660 @default.
- W2893776197 hasBestOaLocation W28937761972 @default.
- W2893776197 hasConcept C108583219 @default.
- W2893776197 hasConcept C116834253 @default.
- W2893776197 hasConcept C13280743 @default.
- W2893776197 hasConcept C153180895 @default.
- W2893776197 hasConcept C154945302 @default.
- W2893776197 hasConcept C162324750 @default.
- W2893776197 hasConcept C165696696 @default.
- W2893776197 hasConcept C185798385 @default.
- W2893776197 hasConcept C187736073 @default.
- W2893776197 hasConcept C204321447 @default.
- W2893776197 hasConcept C205649164 @default.
- W2893776197 hasConcept C2524010 @default.
- W2893776197 hasConcept C2780451532 @default.
- W2893776197 hasConcept C28006648 @default.
- W2893776197 hasConcept C28490314 @default.
- W2893776197 hasConcept C33923547 @default.
- W2893776197 hasConcept C38652104 @default.
- W2893776197 hasConcept C41008148 @default.
- W2893776197 hasConcept C50644808 @default.
- W2893776197 hasConcept C59822182 @default.
- W2893776197 hasConcept C81363708 @default.
- W2893776197 hasConcept C86803240 @default.
- W2893776197 hasConcept C90805587 @default.
- W2893776197 hasConceptScore W2893776197C108583219 @default.
- W2893776197 hasConceptScore W2893776197C116834253 @default.
- W2893776197 hasConceptScore W2893776197C13280743 @default.
- W2893776197 hasConceptScore W2893776197C153180895 @default.
- W2893776197 hasConceptScore W2893776197C154945302 @default.
- W2893776197 hasConceptScore W2893776197C162324750 @default.
- W2893776197 hasConceptScore W2893776197C165696696 @default.
- W2893776197 hasConceptScore W2893776197C185798385 @default.
- W2893776197 hasConceptScore W2893776197C187736073 @default.
- W2893776197 hasConceptScore W2893776197C204321447 @default.
- W2893776197 hasConceptScore W2893776197C205649164 @default.
- W2893776197 hasConceptScore W2893776197C2524010 @default.
- W2893776197 hasConceptScore W2893776197C2780451532 @default.
- W2893776197 hasConceptScore W2893776197C28006648 @default.
- W2893776197 hasConceptScore W2893776197C28490314 @default.
- W2893776197 hasConceptScore W2893776197C33923547 @default.
- W2893776197 hasConceptScore W2893776197C38652104 @default.
- W2893776197 hasConceptScore W2893776197C41008148 @default.
- W2893776197 hasConceptScore W2893776197C50644808 @default.
- W2893776197 hasConceptScore W2893776197C59822182 @default.
- W2893776197 hasConceptScore W2893776197C81363708 @default.
- W2893776197 hasConceptScore W2893776197C86803240 @default.
- W2893776197 hasConceptScore W2893776197C90805587 @default.
- W2893776197 hasLocation W28937761971 @default.
- W2893776197 hasLocation W28937761972 @default.