Matches in SemOpenAlex for { <https://semopenalex.org/work/W2901890385> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2901890385 endingPage "74161" @default.
- W2901890385 startingPage "74151" @default.
- W2901890385 abstract "This paper presents a novel approach for the detection of tables present in documents, leveraging the potential of deep neural networks. Conventional approaches for table detection rely on heuristics that are error prone and specific to a dataset. In contrast, the presented approach harvests the potential of data to recognize tables of arbitrary layout. Most of the prior approaches for table detection are only applicable to PDFs, whereas, the presented approach directly works on images making it generally applicable to any format. The presented approach is based on a novel combination of deformable CNN with faster R-CNN/FPN. Conventional CNN has a fixed receptive field which is problematic for table detection since tables can be present at arbitrary scales along with arbitrary transformations (orientation). Deformable convolution conditions its receptive field on the input itself allowing it to mold its receptive field according to its input. This adaptation of the receptive field enables the network to cater for tables of arbitrary layout. We evaluated the proposed approach on two major publicly available table detection datasets: ICDAR-2013 and ICDAR-2017 POD. The presented approach was able to surpass the state-of-the-art performance on both ICDAR-2013 and ICDAR-2017 POD datasets with a F-measure of 0.994 and 0.968, respectively, indicating its effectiveness and superiority for the task of table detection." @default.
- W2901890385 created "2018-11-29" @default.
- W2901890385 creator A5053635416 @default.
- W2901890385 creator A5058813180 @default.
- W2901890385 creator A5071991246 @default.
- W2901890385 creator A5073903451 @default.
- W2901890385 creator A5083272976 @default.
- W2901890385 date "2018-01-01" @default.
- W2901890385 modified "2023-10-16" @default.
- W2901890385 title "DeCNT: Deep Deformable CNN for Table Detection" @default.
- W2901890385 cites W1536680647 @default.
- W2901890385 cites W1967830139 @default.
- W2901890385 cites W2009659675 @default.
- W2901890385 cites W2016465393 @default.
- W2901890385 cites W2022351003 @default.
- W2901890385 cites W2046941907 @default.
- W2901890385 cites W2092772700 @default.
- W2901890385 cites W2098218583 @default.
- W2901890385 cites W2107092590 @default.
- W2901890385 cites W2136379584 @default.
- W2901890385 cites W2137998699 @default.
- W2901890385 cites W2150673968 @default.
- W2901890385 cites W2166323498 @default.
- W2901890385 cites W2168459394 @default.
- W2901890385 cites W2321821989 @default.
- W2901890385 cites W2395611524 @default.
- W2901890385 cites W2444353601 @default.
- W2901890385 cites W2601564443 @default.
- W2901890385 cites W2786162033 @default.
- W2901890385 cites W2787523828 @default.
- W2901890385 cites W2962843773 @default.
- W2901890385 cites W4246722913 @default.
- W2901890385 doi "https://doi.org/10.1109/access.2018.2880211" @default.
- W2901890385 hasPublicationYear "2018" @default.
- W2901890385 type Work @default.
- W2901890385 sameAs 2901890385 @default.
- W2901890385 citedByCount "93" @default.
- W2901890385 countsByYear W29018903852019 @default.
- W2901890385 countsByYear W29018903852020 @default.
- W2901890385 countsByYear W29018903852021 @default.
- W2901890385 countsByYear W29018903852022 @default.
- W2901890385 countsByYear W29018903852023 @default.
- W2901890385 crossrefType "journal-article" @default.
- W2901890385 hasAuthorship W2901890385A5053635416 @default.
- W2901890385 hasAuthorship W2901890385A5058813180 @default.
- W2901890385 hasAuthorship W2901890385A5071991246 @default.
- W2901890385 hasAuthorship W2901890385A5073903451 @default.
- W2901890385 hasAuthorship W2901890385A5083272976 @default.
- W2901890385 hasBestOaLocation W29018903851 @default.
- W2901890385 hasConcept C121684516 @default.
- W2901890385 hasConcept C124101348 @default.
- W2901890385 hasConcept C154945302 @default.
- W2901890385 hasConcept C31972630 @default.
- W2901890385 hasConcept C41008148 @default.
- W2901890385 hasConcept C45235069 @default.
- W2901890385 hasConceptScore W2901890385C121684516 @default.
- W2901890385 hasConceptScore W2901890385C124101348 @default.
- W2901890385 hasConceptScore W2901890385C154945302 @default.
- W2901890385 hasConceptScore W2901890385C31972630 @default.
- W2901890385 hasConceptScore W2901890385C41008148 @default.
- W2901890385 hasConceptScore W2901890385C45235069 @default.
- W2901890385 hasFunder F4320309480 @default.
- W2901890385 hasFunder F4320321114 @default.
- W2901890385 hasLocation W29018903851 @default.
- W2901890385 hasOpenAccess W2901890385 @default.
- W2901890385 hasPrimaryLocation W29018903851 @default.
- W2901890385 hasRelatedWork W1891287906 @default.
- W2901890385 hasRelatedWork W1969923398 @default.
- W2901890385 hasRelatedWork W2036807459 @default.
- W2901890385 hasRelatedWork W2058170566 @default.
- W2901890385 hasRelatedWork W2166044122 @default.
- W2901890385 hasRelatedWork W2229312674 @default.
- W2901890385 hasRelatedWork W258625772 @default.
- W2901890385 hasRelatedWork W2755342338 @default.
- W2901890385 hasRelatedWork W2772917594 @default.
- W2901890385 hasRelatedWork W3116076068 @default.
- W2901890385 hasVolume "6" @default.
- W2901890385 isParatext "false" @default.
- W2901890385 isRetracted "false" @default.
- W2901890385 magId "2901890385" @default.
- W2901890385 workType "article" @default.