Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293313290> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W4293313290 abstract "We propose a new approach for paragraph recognition in document images by spatial graph convolutional networks (GCN) applied on OCR text boxes. Two steps, namely line splitting and line clustering, are performed to extract paragraphs from the lines in OCR results. Each step uses a beta-skeleton graph constructed from bounding boxes, where the graph edges provide efficient support for graph convolution operations. With only pure layout input features, the GCN model size is 3~4 orders of magnitude smaller compared to R-CNN based models, while achieving comparable or better accuracies on PubLayNet and other datasets. Furthermore, the GCN models show good generalization from synthetic training data to real-world images, and good adaptivity for variable document styles." @default.
- W4293313290 created "2022-08-27" @default.
- W4293313290 creator A5040714763 @default.
- W4293313290 creator A5078560039 @default.
- W4293313290 creator A5089503656 @default.
- W4293313290 date "2021-01-29" @default.
- W4293313290 modified "2023-10-01" @default.
- W4293313290 title "Post-OCR Paragraph Recognition by Graph Convolutional Networks" @default.
- W4293313290 doi "https://doi.org/10.48550/arxiv.2101.12741" @default.
- W4293313290 hasPublicationYear "2021" @default.
- W4293313290 type Work @default.
- W4293313290 citedByCount "0" @default.
- W4293313290 crossrefType "posted-content" @default.
- W4293313290 hasAuthorship W4293313290A5040714763 @default.
- W4293313290 hasAuthorship W4293313290A5078560039 @default.
- W4293313290 hasAuthorship W4293313290A5089503656 @default.
- W4293313290 hasBestOaLocation W42933132901 @default.
- W4293313290 hasConcept C132525143 @default.
- W4293313290 hasConcept C136764020 @default.
- W4293313290 hasConcept C153180895 @default.
- W4293313290 hasConcept C154945302 @default.
- W4293313290 hasConcept C2777206241 @default.
- W4293313290 hasConcept C41008148 @default.
- W4293313290 hasConcept C45347329 @default.
- W4293313290 hasConcept C50644808 @default.
- W4293313290 hasConcept C63584917 @default.
- W4293313290 hasConcept C73555534 @default.
- W4293313290 hasConcept C80444323 @default.
- W4293313290 hasConcept C81363708 @default.
- W4293313290 hasConceptScore W4293313290C132525143 @default.
- W4293313290 hasConceptScore W4293313290C136764020 @default.
- W4293313290 hasConceptScore W4293313290C153180895 @default.
- W4293313290 hasConceptScore W4293313290C154945302 @default.
- W4293313290 hasConceptScore W4293313290C2777206241 @default.
- W4293313290 hasConceptScore W4293313290C41008148 @default.
- W4293313290 hasConceptScore W4293313290C45347329 @default.
- W4293313290 hasConceptScore W4293313290C50644808 @default.
- W4293313290 hasConceptScore W4293313290C63584917 @default.
- W4293313290 hasConceptScore W4293313290C73555534 @default.
- W4293313290 hasConceptScore W4293313290C80444323 @default.
- W4293313290 hasConceptScore W4293313290C81363708 @default.
- W4293313290 hasLocation W42933132901 @default.
- W4293313290 hasLocation W42933132902 @default.
- W4293313290 hasOpenAccess W4293313290 @default.
- W4293313290 hasPrimaryLocation W42933132901 @default.
- W4293313290 hasRelatedWork W2295021132 @default.
- W4293313290 hasRelatedWork W2755240195 @default.
- W4293313290 hasRelatedWork W2756241593 @default.
- W4293313290 hasRelatedWork W2766634277 @default.
- W4293313290 hasRelatedWork W2767651786 @default.
- W4293313290 hasRelatedWork W2801801420 @default.
- W4293313290 hasRelatedWork W2912288872 @default.
- W4293313290 hasRelatedWork W2964106404 @default.
- W4293313290 hasRelatedWork W4312417841 @default.
- W4293313290 hasRelatedWork W564581980 @default.
- W4293313290 isParatext "false" @default.
- W4293313290 isRetracted "false" @default.
- W4293313290 workType "article" @default.