Matches in SemOpenAlex for { <https://semopenalex.org/work/W2278889731> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2278889731 endingPage "96" @default.
- W2278889731 startingPage "85" @default.
- W2278889731 abstract "This paper focuses on the problem of script identification in scene text images. Facing this problem with state of the art CNN classifiers is not straightforward, as they fail to address a key characteristic of scene text instances: their extremely variable aspect ratio. Instead of resizing input images to a fixed aspect ratio as in the typical use of holistic CNN classifiers, we propose here a patch-based classification framework in order to preserve discriminative parts of the image that are characteristic of its class. We describe a novel method based on the use of ensembles of conjoined networks to jointly learn discriminative stroke-parts representations and their relative importance in a patch-based classification scheme. Our experiments with this learning procedure demonstrate state-of-the-art results in two public script identification datasets. In addition, we propose a new public benchmark dataset for the evaluation of multi-lingual scene text end-to-end reading systems. Experiments done in this dataset demonstrate the key role of script identification in a complete end-to-end system that combines our script identification method with a previously published text detector and an off-the-shelf OCR engine." @default.
- W2278889731 created "2016-06-24" @default.
- W2278889731 creator A5008562740 @default.
- W2278889731 creator A5029375723 @default.
- W2278889731 creator A5034592026 @default.
- W2278889731 date "2017-07-01" @default.
- W2278889731 modified "2023-09-27" @default.
- W2278889731 title "Improving patch-based scene text script identification with ensembles of conjoined networks" @default.
- W2278889731 cites W1965195167 @default.
- W2278889731 cites W1980758230 @default.
- W2278889731 cites W1983364832 @default.
- W2278889731 cites W1990618915 @default.
- W2278889731 cites W1990915430 @default.
- W2278889731 cites W2013657715 @default.
- W2278889731 cites W2037227137 @default.
- W2278889731 cites W2044943596 @default.
- W2278889731 cites W2053642301 @default.
- W2278889731 cites W2071744321 @default.
- W2278889731 cites W2079172786 @default.
- W2278889731 cites W2084413241 @default.
- W2278889731 cites W2094549658 @default.
- W2278889731 cites W2121979056 @default.
- W2278889731 cites W2124404372 @default.
- W2278889731 cites W2136343973 @default.
- W2278889731 cites W2143842970 @default.
- W2278889731 cites W2150881387 @default.
- W2278889731 cites W2171590421 @default.
- W2278889731 cites W2196303045 @default.
- W2278889731 cites W2344822769 @default.
- W2278889731 cites W974261621 @default.
- W2278889731 doi "https://doi.org/10.1016/j.patcog.2017.01.032" @default.
- W2278889731 hasPublicationYear "2017" @default.
- W2278889731 type Work @default.
- W2278889731 sameAs 2278889731 @default.
- W2278889731 citedByCount "68" @default.
- W2278889731 countsByYear W22788897312017 @default.
- W2278889731 countsByYear W22788897312018 @default.
- W2278889731 countsByYear W22788897312019 @default.
- W2278889731 countsByYear W22788897312020 @default.
- W2278889731 countsByYear W22788897312021 @default.
- W2278889731 countsByYear W22788897312022 @default.
- W2278889731 countsByYear W22788897312023 @default.
- W2278889731 crossrefType "journal-article" @default.
- W2278889731 hasAuthorship W2278889731A5008562740 @default.
- W2278889731 hasAuthorship W2278889731A5029375723 @default.
- W2278889731 hasAuthorship W2278889731A5034592026 @default.
- W2278889731 hasBestOaLocation W22788897312 @default.
- W2278889731 hasConcept C116834253 @default.
- W2278889731 hasConcept C119857082 @default.
- W2278889731 hasConcept C13280743 @default.
- W2278889731 hasConcept C153180895 @default.
- W2278889731 hasConcept C154945302 @default.
- W2278889731 hasConcept C185798385 @default.
- W2278889731 hasConcept C205649164 @default.
- W2278889731 hasConcept C26517878 @default.
- W2278889731 hasConcept C38652104 @default.
- W2278889731 hasConcept C41008148 @default.
- W2278889731 hasConcept C59822182 @default.
- W2278889731 hasConcept C86803240 @default.
- W2278889731 hasConcept C97931131 @default.
- W2278889731 hasConceptScore W2278889731C116834253 @default.
- W2278889731 hasConceptScore W2278889731C119857082 @default.
- W2278889731 hasConceptScore W2278889731C13280743 @default.
- W2278889731 hasConceptScore W2278889731C153180895 @default.
- W2278889731 hasConceptScore W2278889731C154945302 @default.
- W2278889731 hasConceptScore W2278889731C185798385 @default.
- W2278889731 hasConceptScore W2278889731C205649164 @default.
- W2278889731 hasConceptScore W2278889731C26517878 @default.
- W2278889731 hasConceptScore W2278889731C38652104 @default.
- W2278889731 hasConceptScore W2278889731C41008148 @default.
- W2278889731 hasConceptScore W2278889731C59822182 @default.
- W2278889731 hasConceptScore W2278889731C86803240 @default.
- W2278889731 hasConceptScore W2278889731C97931131 @default.
- W2278889731 hasLocation W22788897311 @default.
- W2278889731 hasLocation W22788897312 @default.
- W2278889731 hasOpenAccess W2278889731 @default.
- W2278889731 hasPrimaryLocation W22788897311 @default.
- W2278889731 hasRelatedWork W1972656095 @default.
- W2278889731 hasRelatedWork W2024160000 @default.
- W2278889731 hasRelatedWork W2061273563 @default.
- W2278889731 hasRelatedWork W2285052147 @default.
- W2278889731 hasRelatedWork W2729514902 @default.
- W2278889731 hasRelatedWork W2743258233 @default.
- W2278889731 hasRelatedWork W2773500201 @default.
- W2278889731 hasRelatedWork W2970216048 @default.
- W2278889731 hasRelatedWork W2998168123 @default.
- W2278889731 hasRelatedWork W4287995534 @default.
- W2278889731 hasVolume "67" @default.
- W2278889731 isParatext "false" @default.
- W2278889731 isRetracted "false" @default.
- W2278889731 magId "2278889731" @default.
- W2278889731 workType "article" @default.