Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204180818> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3204180818 endingPage "334" @default.
- W3204180818 startingPage "317" @default.
- W3204180818 abstract "Global supply chains are kept viable through the information shared through billions of electronic documents, many of which extensively use tables to display critical information. Making effective supply chain decisions requires the extraction of data from these tables which is hindered by the variations in layouts and styles of tables. In this paper, we propose Table Det: a deep learning based methodology to solve table detection and table image classification in data sheet images in a single inference as the first stage of the table text extraction pipeline. TableDet utilizes Cascade R-CNN with Complete IOU (CIOU) loss and a deformable convolution backbone as its underlying architecture to capture the variations in scales and orientations of tables. It also detects text and figures to enhance its table detection performance. We demonstrate the effectiveness of training TableDet with a dual-step transfer learning process and fine-tuning it with Table Aware Cutout (TAC) augmentation strategy. We achieved the highest F1 score for table detection against state-of-the-art solutions on ICDAR 2013 (complete set), ICDAR 2017 (test set) and ICDAR 2019 (test set) with 100%, 99.3% and 95.1% respectively. For the table image classification task we attained 100% recall and above 85% precision on three test sets. This classification capability ensures that all images with tables would be promoted to the next step in the table text extraction pipeline, with a small number of images without tables making it through." @default.
- W3204180818 created "2021-10-11" @default.
- W3204180818 creator A5003131477 @default.
- W3204180818 creator A5021726620 @default.
- W3204180818 creator A5063328981 @default.
- W3204180818 creator A5074737678 @default.
- W3204180818 date "2022-01-01" @default.
- W3204180818 modified "2023-10-16" @default.
- W3204180818 title "TableDet: An end-to-end deep learning approach for table detection and table image classification in data sheet images" @default.
- W3204180818 cites W2022351003 @default.
- W3204180818 cites W2108598243 @default.
- W3204180818 cites W2520607223 @default.
- W3204180818 cites W2762731413 @default.
- W3204180818 cites W2786162033 @default.
- W3204180818 cites W2787835872 @default.
- W3204180818 cites W2901890385 @default.
- W3204180818 cites W2971712385 @default.
- W3204180818 cites W2997747012 @default.
- W3204180818 cites W2998508940 @default.
- W3204180818 cites W3003496674 @default.
- W3204180818 cites W3003760744 @default.
- W3204180818 cites W3004042913 @default.
- W3204180818 cites W3005638477 @default.
- W3204180818 cites W3011655081 @default.
- W3204180818 cites W3126481501 @default.
- W3204180818 cites W639708223 @default.
- W3204180818 doi "https://doi.org/10.1016/j.neucom.2021.10.023" @default.
- W3204180818 hasPublicationYear "2022" @default.
- W3204180818 type Work @default.
- W3204180818 sameAs 3204180818 @default.
- W3204180818 citedByCount "11" @default.
- W3204180818 countsByYear W32041808182022 @default.
- W3204180818 countsByYear W32041808182023 @default.
- W3204180818 crossrefType "journal-article" @default.
- W3204180818 hasAuthorship W3204180818A5003131477 @default.
- W3204180818 hasAuthorship W3204180818A5021726620 @default.
- W3204180818 hasAuthorship W3204180818A5063328981 @default.
- W3204180818 hasAuthorship W3204180818A5074737678 @default.
- W3204180818 hasConcept C108583219 @default.
- W3204180818 hasConcept C124101348 @default.
- W3204180818 hasConcept C153180895 @default.
- W3204180818 hasConcept C154945302 @default.
- W3204180818 hasConcept C162324750 @default.
- W3204180818 hasConcept C169903167 @default.
- W3204180818 hasConcept C177264268 @default.
- W3204180818 hasConcept C187736073 @default.
- W3204180818 hasConcept C199360897 @default.
- W3204180818 hasConcept C2780451532 @default.
- W3204180818 hasConcept C41008148 @default.
- W3204180818 hasConcept C43521106 @default.
- W3204180818 hasConcept C45235069 @default.
- W3204180818 hasConcept C58489278 @default.
- W3204180818 hasConceptScore W3204180818C108583219 @default.
- W3204180818 hasConceptScore W3204180818C124101348 @default.
- W3204180818 hasConceptScore W3204180818C153180895 @default.
- W3204180818 hasConceptScore W3204180818C154945302 @default.
- W3204180818 hasConceptScore W3204180818C162324750 @default.
- W3204180818 hasConceptScore W3204180818C169903167 @default.
- W3204180818 hasConceptScore W3204180818C177264268 @default.
- W3204180818 hasConceptScore W3204180818C187736073 @default.
- W3204180818 hasConceptScore W3204180818C199360897 @default.
- W3204180818 hasConceptScore W3204180818C2780451532 @default.
- W3204180818 hasConceptScore W3204180818C41008148 @default.
- W3204180818 hasConceptScore W3204180818C43521106 @default.
- W3204180818 hasConceptScore W3204180818C45235069 @default.
- W3204180818 hasConceptScore W3204180818C58489278 @default.
- W3204180818 hasFunder F4320322675 @default.
- W3204180818 hasLocation W32041808181 @default.
- W3204180818 hasOpenAccess W3204180818 @default.
- W3204180818 hasPrimaryLocation W32041808181 @default.
- W3204180818 hasRelatedWork W1990237101 @default.
- W3204180818 hasRelatedWork W2183488467 @default.
- W3204180818 hasRelatedWork W2187490799 @default.
- W3204180818 hasRelatedWork W2790141222 @default.
- W3204180818 hasRelatedWork W2997155179 @default.
- W3204180818 hasRelatedWork W3099765033 @default.
- W3204180818 hasRelatedWork W3170838353 @default.
- W3204180818 hasRelatedWork W4300172249 @default.
- W3204180818 hasRelatedWork W4309907966 @default.
- W3204180818 hasRelatedWork W4387327236 @default.
- W3204180818 hasVolume "468" @default.
- W3204180818 isParatext "false" @default.
- W3204180818 isRetracted "false" @default.
- W3204180818 magId "3204180818" @default.
- W3204180818 workType "article" @default.