Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304080492> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4304080492 abstract "Table is a widely used data form in webpages, spreadsheets, or PDFs to organize and present structural data. Although studies on table structure recognition have been successfully used to convert image-based tables into digital structural formats, solving many real problems still relies on further understanding of the table, such as cell relationship extraction. The current datasets related to table understanding are all based on the digit format. To boost research development, we release a new benchmark named ComFinTab with rich annotations that support both table recognition and understanding tasks. Unlike previous datasets containing the basic tables, ComFinTab contains a large ratio of compound tables, which is much more challenging and requires methods using multiple information sources. Based on the dataset, we also propose a uniform, concise task form with the evaluation metric to better evaluate the model's performance on the table understanding task in compound tables. Finally, a framework named CTUNet is proposed to integrate the compromised visual, semantic, and position features with a graph attention network, which can solve the table recognition task and the challenging table understanding task as a whole. Experimental results compared with some previous advanced table understanding methods demonstrate the effectiveness of our proposed model. Code and dataset are available at urlhttps://github.com/hikopensource/DAVAR-Lab-OCR." @default.
- W4304080492 created "2022-10-10" @default.
- W4304080492 creator A5007634402 @default.
- W4304080492 creator A5011185036 @default.
- W4304080492 creator A5014394467 @default.
- W4304080492 creator A5019611473 @default.
- W4304080492 creator A5026297587 @default.
- W4304080492 creator A5056078581 @default.
- W4304080492 creator A5064842058 @default.
- W4304080492 creator A5085955762 @default.
- W4304080492 date "2022-10-10" @default.
- W4304080492 modified "2023-09-28" @default.
- W4304080492 title "End-to-End Compound Table Understanding with Multi-Modal Modeling" @default.
- W4304080492 cites W2001642682 @default.
- W4304080492 cites W2021167849 @default.
- W4304080492 cites W2051265407 @default.
- W4304080492 cites W2138556038 @default.
- W4304080492 cites W2150673968 @default.
- W4304080492 cites W2154764394 @default.
- W4304080492 cites W2290320465 @default.
- W4304080492 cites W2342096063 @default.
- W4304080492 cites W2483402000 @default.
- W4304080492 cites W2604225376 @default.
- W4304080492 cites W2786162033 @default.
- W4304080492 cites W2810376801 @default.
- W4304080492 cites W2963091658 @default.
- W4304080492 cites W3003206728 @default.
- W4304080492 cites W3003496674 @default.
- W4304080492 cites W3003760744 @default.
- W4304080492 cites W3034556525 @default.
- W4304080492 cites W3034997246 @default.
- W4304080492 cites W3061754956 @default.
- W4304080492 cites W3088604029 @default.
- W4304080492 cites W3093787307 @default.
- W4304080492 cites W3098495697 @default.
- W4304080492 cites W3101082165 @default.
- W4304080492 cites W3107064625 @default.
- W4304080492 cites W3109870706 @default.
- W4304080492 cites W3118722740 @default.
- W4304080492 cites W3167404434 @default.
- W4304080492 cites W3168052339 @default.
- W4304080492 cites W3173486678 @default.
- W4304080492 cites W3180751782 @default.
- W4304080492 cites W3207083256 @default.
- W4304080492 cites W4214693170 @default.
- W4304080492 doi "https://doi.org/10.1145/3503161.3547885" @default.
- W4304080492 hasPublicationYear "2022" @default.
- W4304080492 type Work @default.
- W4304080492 citedByCount "0" @default.
- W4304080492 crossrefType "proceedings-article" @default.
- W4304080492 hasAuthorship W4304080492A5007634402 @default.
- W4304080492 hasAuthorship W4304080492A5011185036 @default.
- W4304080492 hasAuthorship W4304080492A5014394467 @default.
- W4304080492 hasAuthorship W4304080492A5019611473 @default.
- W4304080492 hasAuthorship W4304080492A5026297587 @default.
- W4304080492 hasAuthorship W4304080492A5056078581 @default.
- W4304080492 hasAuthorship W4304080492A5064842058 @default.
- W4304080492 hasAuthorship W4304080492A5085955762 @default.
- W4304080492 hasConcept C154945302 @default.
- W4304080492 hasConcept C188027245 @default.
- W4304080492 hasConcept C192562407 @default.
- W4304080492 hasConcept C41008148 @default.
- W4304080492 hasConcept C45235069 @default.
- W4304080492 hasConcept C71139939 @default.
- W4304080492 hasConcept C74296488 @default.
- W4304080492 hasConcept C77088390 @default.
- W4304080492 hasConceptScore W4304080492C154945302 @default.
- W4304080492 hasConceptScore W4304080492C188027245 @default.
- W4304080492 hasConceptScore W4304080492C192562407 @default.
- W4304080492 hasConceptScore W4304080492C41008148 @default.
- W4304080492 hasConceptScore W4304080492C45235069 @default.
- W4304080492 hasConceptScore W4304080492C71139939 @default.
- W4304080492 hasConceptScore W4304080492C74296488 @default.
- W4304080492 hasConceptScore W4304080492C77088390 @default.
- W4304080492 hasLocation W43040804921 @default.
- W4304080492 hasOpenAccess W4304080492 @default.
- W4304080492 hasPrimaryLocation W43040804921 @default.
- W4304080492 hasRelatedWork W2056254149 @default.
- W4304080492 hasRelatedWork W2161144997 @default.
- W4304080492 hasRelatedWork W2355525742 @default.
- W4304080492 hasRelatedWork W2357325779 @default.
- W4304080492 hasRelatedWork W2359068514 @default.
- W4304080492 hasRelatedWork W2373668538 @default.
- W4304080492 hasRelatedWork W2381871331 @default.
- W4304080492 hasRelatedWork W2385034530 @default.
- W4304080492 hasRelatedWork W2392813427 @default.
- W4304080492 hasRelatedWork W3049547150 @default.
- W4304080492 isParatext "false" @default.
- W4304080492 isRetracted "false" @default.
- W4304080492 workType "article" @default.