Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313303741> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4313303741 abstract "Page layout analysis is a fundamental step in document processing which enables to segment a page into regions of interest. With highly complex layouts and mixed scripts, scholarly commentaries are text-heavy documents which remain challenging for state-of-the-art models. Their layout considerably varies across editions and their most important regions are mainly defined by semantic rather than graphical characteristics such as position or appearance. This setting calls for a comparison between textual, visual and hybrid approaches. We therefore assess the performances of two transformers (LayoutLMv3 and RoBERTa) and an objection-detection network (YOLOv5). If results show a clear advantage in favor of the latter, we also list several caveats to this finding. In addition to our experiments, we release a dataset of ca. 300 annotated pages sampled from 19th century commentaries." @default.
- W4313303741 created "2023-01-06" @default.
- W4313303741 creator A5036246506 @default.
- W4313303741 creator A5059704742 @default.
- W4313303741 date "2022-12-12" @default.
- W4313303741 modified "2023-09-23" @default.
- W4313303741 title "Page Layout Analysis of Text-heavy Historical Documents: a Comparison of Textual and Visual Approaches" @default.
- W4313303741 doi "https://doi.org/10.48550/arxiv.2212.13924" @default.
- W4313303741 hasPublicationYear "2022" @default.
- W4313303741 type Work @default.
- W4313303741 citedByCount "0" @default.
- W4313303741 crossrefType "posted-content" @default.
- W4313303741 hasAuthorship W4313303741A5036246506 @default.
- W4313303741 hasAuthorship W4313303741A5059704742 @default.
- W4313303741 hasBestOaLocation W43133037411 @default.
- W4313303741 hasConcept C115961682 @default.
- W4313303741 hasConcept C121332964 @default.
- W4313303741 hasConcept C142362112 @default.
- W4313303741 hasConcept C153349607 @default.
- W4313303741 hasConcept C154945302 @default.
- W4313303741 hasConcept C165801399 @default.
- W4313303741 hasConcept C188985296 @default.
- W4313303741 hasConcept C199360897 @default.
- W4313303741 hasConcept C204321447 @default.
- W4313303741 hasConcept C23123220 @default.
- W4313303741 hasConcept C41008148 @default.
- W4313303741 hasConcept C61423126 @default.
- W4313303741 hasConcept C62520636 @default.
- W4313303741 hasConcept C66322947 @default.
- W4313303741 hasConcept C72773152 @default.
- W4313303741 hasConceptScore W4313303741C115961682 @default.
- W4313303741 hasConceptScore W4313303741C121332964 @default.
- W4313303741 hasConceptScore W4313303741C142362112 @default.
- W4313303741 hasConceptScore W4313303741C153349607 @default.
- W4313303741 hasConceptScore W4313303741C154945302 @default.
- W4313303741 hasConceptScore W4313303741C165801399 @default.
- W4313303741 hasConceptScore W4313303741C188985296 @default.
- W4313303741 hasConceptScore W4313303741C199360897 @default.
- W4313303741 hasConceptScore W4313303741C204321447 @default.
- W4313303741 hasConceptScore W4313303741C23123220 @default.
- W4313303741 hasConceptScore W4313303741C41008148 @default.
- W4313303741 hasConceptScore W4313303741C61423126 @default.
- W4313303741 hasConceptScore W4313303741C62520636 @default.
- W4313303741 hasConceptScore W4313303741C66322947 @default.
- W4313303741 hasConceptScore W4313303741C72773152 @default.
- W4313303741 hasLocation W43133037411 @default.
- W4313303741 hasOpenAccess W4313303741 @default.
- W4313303741 hasPrimaryLocation W43133037411 @default.
- W4313303741 hasRelatedWork W1530957558 @default.
- W4313303741 hasRelatedWork W1998951530 @default.
- W4313303741 hasRelatedWork W2086733238 @default.
- W4313303741 hasRelatedWork W2163126033 @default.
- W4313303741 hasRelatedWork W2320875372 @default.
- W4313303741 hasRelatedWork W2368424885 @default.
- W4313303741 hasRelatedWork W2372778180 @default.
- W4313303741 hasRelatedWork W2384888906 @default.
- W4313303741 hasRelatedWork W2529681551 @default.
- W4313303741 hasRelatedWork W2980391053 @default.
- W4313303741 isParatext "false" @default.
- W4313303741 isRetracted "false" @default.
- W4313303741 workType "article" @default.