Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312980945> ?p ?o ?g. }
- W4312980945 endingPage "17" @default.
- W4312980945 startingPage "3" @default.
- W4312980945 abstract "AbstractDespite recent advances in automatic text recognition, the performance remains moderate when it comes to historical manuscripts. This is mainly because of the scarcity of available labelled data to train the data-hungry Handwritten Text Recognition (HTR) models. The Keyword Spotting System (KWS) provides a valid alternative to HTR due to the reduction in error rate, but it is usually limited to a closed reference vocabulary. In this paper, we propose a few-shot learning paradigm for spotting sequences of a few characters (N-gram) that requires a small amount of labelled training data. We exhibit that recognition of important n-grams could reduce the system’s dependency on vocabulary. In this case, an out-of-vocabulary (OOV) word in an input handwritten line image could be a sequence of n-grams that belong to the lexicon. An extensive experimental evaluation of our proposed multi-representation approach was carried out on a subset of Bentham’s historical manuscript collections to obtain some really promising results in this direction.KeywordsN-gram spottingFew-shot learningMultimodal understandingHistorical handwritten collections" @default.
- W4312980945 created "2023-01-05" @default.
- W4312980945 creator A5023531500 @default.
- W4312980945 creator A5044248405 @default.
- W4312980945 creator A5048265453 @default.
- W4312980945 creator A5060424729 @default.
- W4312980945 creator A5065907624 @default.
- W4312980945 creator A5072951767 @default.
- W4312980945 creator A5090099386 @default.
- W4312980945 date "2022-01-01" @default.
- W4312980945 modified "2023-09-29" @default.
- W4312980945 title "A Few Shot Multi-representation Approach for N-Gram Spotting in Historical Manuscripts" @default.
- W4312980945 cites W1151768060 @default.
- W4312980945 cites W1978065852 @default.
- W4312980945 cites W2002629090 @default.
- W4312980945 cites W2010870255 @default.
- W4312980945 cites W2038039799 @default.
- W4312980945 cites W2053317383 @default.
- W4312980945 cites W2061994628 @default.
- W4312980945 cites W2103667008 @default.
- W4312980945 cites W2128060444 @default.
- W4312980945 cites W2141356776 @default.
- W4312980945 cites W2152928267 @default.
- W4312980945 cites W2194321275 @default.
- W4312980945 cites W2194775991 @default.
- W4312980945 cites W2291723904 @default.
- W4312980945 cites W2339223376 @default.
- W4312980945 cites W2481930807 @default.
- W4312980945 cites W274356433 @default.
- W4312980945 cites W2795728481 @default.
- W4312980945 cites W2963908984 @default.
- W4312980945 cites W2966055673 @default.
- W4312980945 cites W3092694106 @default.
- W4312980945 cites W3093265417 @default.
- W4312980945 cites W3107976279 @default.
- W4312980945 cites W3109645351 @default.
- W4312980945 cites W3163599761 @default.
- W4312980945 cites W3183607969 @default.
- W4312980945 cites W3194824089 @default.
- W4312980945 cites W3201833923 @default.
- W4312980945 cites W3211060597 @default.
- W4312980945 cites W4238410424 @default.
- W4312980945 doi "https://doi.org/10.1007/978-3-031-21648-0_1" @default.
- W4312980945 hasPublicationYear "2022" @default.
- W4312980945 type Work @default.
- W4312980945 citedByCount "0" @default.
- W4312980945 crossrefType "book-chapter" @default.
- W4312980945 hasAuthorship W4312980945A5023531500 @default.
- W4312980945 hasAuthorship W4312980945A5044248405 @default.
- W4312980945 hasAuthorship W4312980945A5048265453 @default.
- W4312980945 hasAuthorship W4312980945A5060424729 @default.
- W4312980945 hasAuthorship W4312980945A5065907624 @default.
- W4312980945 hasAuthorship W4312980945A5072951767 @default.
- W4312980945 hasAuthorship W4312980945A5090099386 @default.
- W4312980945 hasBestOaLocation W43129809452 @default.
- W4312980945 hasConcept C117884012 @default.
- W4312980945 hasConcept C137293760 @default.
- W4312980945 hasConcept C138885662 @default.
- W4312980945 hasConcept C153180895 @default.
- W4312980945 hasConcept C154945302 @default.
- W4312980945 hasConcept C17744445 @default.
- W4312980945 hasConcept C178790620 @default.
- W4312980945 hasConcept C185592680 @default.
- W4312980945 hasConcept C19768560 @default.
- W4312980945 hasConcept C199539241 @default.
- W4312980945 hasConcept C204321447 @default.
- W4312980945 hasConcept C2776359362 @default.
- W4312980945 hasConcept C2777601683 @default.
- W4312980945 hasConcept C2778112365 @default.
- W4312980945 hasConcept C2778121359 @default.
- W4312980945 hasConcept C2778344882 @default.
- W4312980945 hasConcept C2779506182 @default.
- W4312980945 hasConcept C2781213101 @default.
- W4312980945 hasConcept C28490314 @default.
- W4312980945 hasConcept C40969351 @default.
- W4312980945 hasConcept C41008148 @default.
- W4312980945 hasConcept C41895202 @default.
- W4312980945 hasConcept C54355233 @default.
- W4312980945 hasConcept C86803240 @default.
- W4312980945 hasConcept C90805587 @default.
- W4312980945 hasConcept C94625758 @default.
- W4312980945 hasConceptScore W4312980945C117884012 @default.
- W4312980945 hasConceptScore W4312980945C137293760 @default.
- W4312980945 hasConceptScore W4312980945C138885662 @default.
- W4312980945 hasConceptScore W4312980945C153180895 @default.
- W4312980945 hasConceptScore W4312980945C154945302 @default.
- W4312980945 hasConceptScore W4312980945C17744445 @default.
- W4312980945 hasConceptScore W4312980945C178790620 @default.
- W4312980945 hasConceptScore W4312980945C185592680 @default.
- W4312980945 hasConceptScore W4312980945C19768560 @default.
- W4312980945 hasConceptScore W4312980945C199539241 @default.
- W4312980945 hasConceptScore W4312980945C204321447 @default.
- W4312980945 hasConceptScore W4312980945C2776359362 @default.
- W4312980945 hasConceptScore W4312980945C2777601683 @default.
- W4312980945 hasConceptScore W4312980945C2778112365 @default.
- W4312980945 hasConceptScore W4312980945C2778121359 @default.
- W4312980945 hasConceptScore W4312980945C2778344882 @default.
- W4312980945 hasConceptScore W4312980945C2779506182 @default.