Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386598385> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4386598385 abstract "Scene text segmentation task has numerous practical applications. However, the number of images in the available datasets for scene text segmentation is too small to effectively train deep learning-based models, leading to limited performance. To solve this problem, we perform the segmentation in two aspects: paired data synthesis and methodology. The former is executed via the proposed Text Image-conditional GANs to generate realistic paired data. We exploit real-world images by self-supervised pre-training scheme via inpainting approach before training the proposed GANs to produce realistic synthetic data. The latter is carried out by the proposed scene text segmentation network to optimize learning the generated paired data, called Multi-task Cascade Transformer. It includes two auxiliary tasks and one main task for text segmentation. The functions of the two auxiliary tasks are to learn the text region to focus on, together with learning the structure of text through their fonts, and then they support the main task. We implement three publicly available datasets for scene text segmentation: ICDAR13 FST, Total Text, and TextSeg datasets to demonstrate the effectiveness of our method. Our experimental result outperforms existing methods." @default.
- W4386598385 created "2023-09-12" @default.
- W4386598385 creator A5070936425 @default.
- W4386598385 creator A5076385867 @default.
- W4386598385 date "2023-10-08" @default.
- W4386598385 modified "2023-09-30" @default.
- W4386598385 title "Scene Text Segmentation by Paired Data Synthesis" @default.
- W4386598385 cites W1922126009 @default.
- W4386598385 cites W2008806374 @default.
- W4386598385 cites W2028045978 @default.
- W4386598385 cites W2574887079 @default.
- W4386598385 cites W2963299604 @default.
- W4386598385 cites W2963800363 @default.
- W4386598385 cites W2982148195 @default.
- W4386598385 cites W2991090032 @default.
- W4386598385 cites W3136958399 @default.
- W4386598385 cites W3157525179 @default.
- W4386598385 cites W3168428721 @default.
- W4386598385 cites W3199003182 @default.
- W4386598385 cites W3199738066 @default.
- W4386598385 cites W4383112434 @default.
- W4386598385 doi "https://doi.org/10.1109/icip49359.2023.10222845" @default.
- W4386598385 hasPublicationYear "2023" @default.
- W4386598385 type Work @default.
- W4386598385 citedByCount "0" @default.
- W4386598385 crossrefType "proceedings-article" @default.
- W4386598385 hasAuthorship W4386598385A5070936425 @default.
- W4386598385 hasAuthorship W4386598385A5076385867 @default.
- W4386598385 hasBestOaLocation W43865983851 @default.
- W4386598385 hasConcept C108583219 @default.
- W4386598385 hasConcept C115961682 @default.
- W4386598385 hasConcept C11727466 @default.
- W4386598385 hasConcept C119857082 @default.
- W4386598385 hasConcept C120665830 @default.
- W4386598385 hasConcept C121332964 @default.
- W4386598385 hasConcept C124504099 @default.
- W4386598385 hasConcept C153180895 @default.
- W4386598385 hasConcept C154945302 @default.
- W4386598385 hasConcept C162324750 @default.
- W4386598385 hasConcept C165696696 @default.
- W4386598385 hasConcept C165801399 @default.
- W4386598385 hasConcept C187736073 @default.
- W4386598385 hasConcept C192209626 @default.
- W4386598385 hasConcept C2776145971 @default.
- W4386598385 hasConcept C2780451532 @default.
- W4386598385 hasConcept C38652104 @default.
- W4386598385 hasConcept C41008148 @default.
- W4386598385 hasConcept C62520636 @default.
- W4386598385 hasConcept C65885262 @default.
- W4386598385 hasConcept C66322947 @default.
- W4386598385 hasConcept C89600930 @default.
- W4386598385 hasConceptScore W4386598385C108583219 @default.
- W4386598385 hasConceptScore W4386598385C115961682 @default.
- W4386598385 hasConceptScore W4386598385C11727466 @default.
- W4386598385 hasConceptScore W4386598385C119857082 @default.
- W4386598385 hasConceptScore W4386598385C120665830 @default.
- W4386598385 hasConceptScore W4386598385C121332964 @default.
- W4386598385 hasConceptScore W4386598385C124504099 @default.
- W4386598385 hasConceptScore W4386598385C153180895 @default.
- W4386598385 hasConceptScore W4386598385C154945302 @default.
- W4386598385 hasConceptScore W4386598385C162324750 @default.
- W4386598385 hasConceptScore W4386598385C165696696 @default.
- W4386598385 hasConceptScore W4386598385C165801399 @default.
- W4386598385 hasConceptScore W4386598385C187736073 @default.
- W4386598385 hasConceptScore W4386598385C192209626 @default.
- W4386598385 hasConceptScore W4386598385C2776145971 @default.
- W4386598385 hasConceptScore W4386598385C2780451532 @default.
- W4386598385 hasConceptScore W4386598385C38652104 @default.
- W4386598385 hasConceptScore W4386598385C41008148 @default.
- W4386598385 hasConceptScore W4386598385C62520636 @default.
- W4386598385 hasConceptScore W4386598385C65885262 @default.
- W4386598385 hasConceptScore W4386598385C66322947 @default.
- W4386598385 hasConceptScore W4386598385C89600930 @default.
- W4386598385 hasFunder F4320311687 @default.
- W4386598385 hasFunder F4320320671 @default.
- W4386598385 hasLocation W43865983851 @default.
- W4386598385 hasOpenAccess W4386598385 @default.
- W4386598385 hasPrimaryLocation W43865983851 @default.
- W4386598385 hasRelatedWork W134976887 @default.
- W4386598385 hasRelatedWork W1582206143 @default.
- W4386598385 hasRelatedWork W1840273037 @default.
- W4386598385 hasRelatedWork W2021143974 @default.
- W4386598385 hasRelatedWork W2052361277 @default.
- W4386598385 hasRelatedWork W2117933325 @default.
- W4386598385 hasRelatedWork W2549765251 @default.
- W4386598385 hasRelatedWork W2954384599 @default.
- W4386598385 hasRelatedWork W3168029802 @default.
- W4386598385 hasRelatedWork W4285827401 @default.
- W4386598385 isParatext "false" @default.
- W4386598385 isRetracted "false" @default.
- W4386598385 workType "article" @default.