Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312843676> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4312843676 endingPage "561" @default.
- W4312843676 startingPage "545" @default.
- W4312843676 abstract "Tables are a widely used and efficient data structure. Although people can intuitively understand table contents, it remains challenging for machines, especially the tables taken in the wild. Previous methods mainly focus on scanned or PDF tables, but ignore investigating camera-based tables. This paper treats table structure recognition (TSR) as an image-to-sequence recognition task and adopts an end-to-end trainable model for complex TSR in the wild. Specifically, the model consists of a CNN-based encoder and two Transformer-based decoding branches, which can simultaneously predict the logical and physical structures of a table. Currently available camera-based table datasets are scarce, but deep learning methods heavily rely on large-scale datasets. To alleviate data insufficiency and boost model’s performance, we propose a new and effective table data augmentation method, called TabSplitter. Due to the complex structure caused by cells spanning multiple rows or columns, directly cropping will lead to damage and change the properties of these cells. To solve this problem, we proposed a matrix representation, named Identity Matrix (IM), to describe the table structure. Based on IM, we crop the tables and correct the cells whose attributes have changed, thus enhancing data diversity. Furthermore, the proposed IM facilitates the pre-processing of data and post-processing of predictions. Experimental results on several datasets demonstrate the effectiveness of the model and the TabSplitter for TSR, especially for complex tables in the wild." @default.
- W4312843676 created "2023-01-05" @default.
- W4312843676 creator A5012042767 @default.
- W4312843676 creator A5048415763 @default.
- W4312843676 creator A5056516308 @default.
- W4312843676 creator A5080674767 @default.
- W4312843676 creator A5085010670 @default.
- W4312843676 date "2022-01-01" @default.
- W4312843676 modified "2023-10-16" @default.
- W4312843676 title "Complex Table Structure Recognition in the Wild Using Transformer and Identity Matrix-Based Augmentation" @default.
- W4312843676 cites W1573796710 @default.
- W4312843676 cites W1903029394 @default.
- W4312843676 cites W2127141656 @default.
- W4312843676 cites W2194187530 @default.
- W4312843676 cites W2194775991 @default.
- W4312843676 cites W2786162033 @default.
- W4312843676 cites W2978036638 @default.
- W4312843676 cites W2999605892 @default.
- W4312843676 cites W3003206728 @default.
- W4312843676 cites W3003496674 @default.
- W4312843676 cites W3003931580 @default.
- W4312843676 cites W3034997246 @default.
- W4312843676 cites W3107064625 @default.
- W4312843676 cites W3109870706 @default.
- W4312843676 cites W3118722740 @default.
- W4312843676 cites W3134658493 @default.
- W4312843676 cites W3154615938 @default.
- W4312843676 cites W3176384932 @default.
- W4312843676 cites W3201922353 @default.
- W4312843676 cites W3201979934 @default.
- W4312843676 cites W3207083256 @default.
- W4312843676 cites W4214693170 @default.
- W4312843676 cites W4246722913 @default.
- W4312843676 cites W4312554912 @default.
- W4312843676 doi "https://doi.org/10.1007/978-3-031-21648-0_37" @default.
- W4312843676 hasPublicationYear "2022" @default.
- W4312843676 type Work @default.
- W4312843676 citedByCount "1" @default.
- W4312843676 countsByYear W43128436762023 @default.
- W4312843676 crossrefType "book-chapter" @default.
- W4312843676 hasAuthorship W4312843676A5012042767 @default.
- W4312843676 hasAuthorship W4312843676A5048415763 @default.
- W4312843676 hasAuthorship W4312843676A5056516308 @default.
- W4312843676 hasAuthorship W4312843676A5080674767 @default.
- W4312843676 hasAuthorship W4312843676A5085010670 @default.
- W4312843676 hasConcept C119857082 @default.
- W4312843676 hasConcept C124101348 @default.
- W4312843676 hasConcept C135598885 @default.
- W4312843676 hasConcept C153180895 @default.
- W4312843676 hasConcept C154945302 @default.
- W4312843676 hasConcept C41008148 @default.
- W4312843676 hasConcept C45235069 @default.
- W4312843676 hasConcept C77088390 @default.
- W4312843676 hasConceptScore W4312843676C119857082 @default.
- W4312843676 hasConceptScore W4312843676C124101348 @default.
- W4312843676 hasConceptScore W4312843676C135598885 @default.
- W4312843676 hasConceptScore W4312843676C153180895 @default.
- W4312843676 hasConceptScore W4312843676C154945302 @default.
- W4312843676 hasConceptScore W4312843676C41008148 @default.
- W4312843676 hasConceptScore W4312843676C45235069 @default.
- W4312843676 hasConceptScore W4312843676C77088390 @default.
- W4312843676 hasLocation W43128436761 @default.
- W4312843676 hasOpenAccess W4312843676 @default.
- W4312843676 hasPrimaryLocation W43128436761 @default.
- W4312843676 hasRelatedWork W1519332147 @default.
- W4312843676 hasRelatedWork W2070384782 @default.
- W4312843676 hasRelatedWork W2390933768 @default.
- W4312843676 hasRelatedWork W2982353255 @default.
- W4312843676 hasRelatedWork W3122529031 @default.
- W4312843676 hasRelatedWork W4206785508 @default.
- W4312843676 hasRelatedWork W4226523698 @default.
- W4312843676 hasRelatedWork W4235300586 @default.
- W4312843676 hasRelatedWork W4281971614 @default.
- W4312843676 hasRelatedWork W4385281412 @default.
- W4312843676 isParatext "false" @default.
- W4312843676 isRetracted "false" @default.
- W4312843676 workType "book-chapter" @default.