Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385990911> ?p ?o ?g. }
- W4385990911 endingPage "76" @default.
- W4385990911 startingPage "51" @default.
- W4385990911 abstract "Table detection is the task of classifying and localizing table objects within document images. With the recent development in deep learning methods, we observe remarkable success in table detection. However, a significant amount of labeled data is required to train these models effectively. Many semi-supervised approaches are introduced to mitigate the need for a substantial amount of label data. These approaches use CNN-based detectors that rely on anchor proposals and post-processing stages such as NMS. To tackle these limitations, this paper presents a novel end-to-end semi-supervised table detection method that employs the deformable transformer for detecting table objects. We evaluate our semi-supervised method on PubLayNet, DocBank, ICADR-19 and TableBank datasets, and it achieves superior performance compared to previous methods. It outperforms the fully supervised method (Deformable transformer) by +3.4 points on 10% labels of TableBank-both dataset and the previous CNN-based semi-supervised approach (Soft Teacher) by +1.8 points on 10% labels of PubLayNet dataset. We hope this work opens new possibilities towards semi-supervised and unsupervised table detection methods." @default.
- W4385990911 created "2023-08-19" @default.
- W4385990911 creator A5051437282 @default.
- W4385990911 creator A5051650277 @default.
- W4385990911 creator A5065666680 @default.
- W4385990911 creator A5073619925 @default.
- W4385990911 creator A5086894159 @default.
- W4385990911 date "2023-01-01" @default.
- W4385990911 modified "2023-10-14" @default.
- W4385990911 title "Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer" @default.
- W4385990911 cites W1536680647 @default.
- W4385990911 cites W1861492603 @default.
- W4385990911 cites W1903029394 @default.
- W4385990911 cites W1967830139 @default.
- W4385990911 cites W1970549718 @default.
- W4385990911 cites W2016465393 @default.
- W4385990911 cites W2022351003 @default.
- W4385990911 cites W2046941907 @default.
- W4385990911 cites W2107092590 @default.
- W4385990911 cites W2121061496 @default.
- W4385990911 cites W2136379584 @default.
- W4385990911 cites W2166323498 @default.
- W4385990911 cites W2222512263 @default.
- W4385990911 cites W2444353601 @default.
- W4385990911 cites W2565639579 @default.
- W4385990911 cites W2570343428 @default.
- W4385990911 cites W2601564443 @default.
- W4385990911 cites W2620069838 @default.
- W4385990911 cites W2785462444 @default.
- W4385990911 cites W2786162033 @default.
- W4385990911 cites W2786480153 @default.
- W4385990911 cites W2787523828 @default.
- W4385990911 cites W2787835872 @default.
- W4385990911 cites W2804915017 @default.
- W4385990911 cites W2901890385 @default.
- W4385990911 cites W2902089218 @default.
- W4385990911 cites W2910897241 @default.
- W4385990911 cites W2944369145 @default.
- W4385990911 cites W2963150697 @default.
- W4385990911 cites W2963296620 @default.
- W4385990911 cites W2963351448 @default.
- W4385990911 cites W2963785012 @default.
- W4385990911 cites W2964241181 @default.
- W4385990911 cites W2964346820 @default.
- W4385990911 cites W2964350391 @default.
- W4385990911 cites W2966926453 @default.
- W4385990911 cites W2981413347 @default.
- W4385990911 cites W2986271972 @default.
- W4385990911 cites W3003334191 @default.
- W4385990911 cites W3003496674 @default.
- W4385990911 cites W3003711898 @default.
- W4385990911 cites W3003760744 @default.
- W4385990911 cites W3004042913 @default.
- W4385990911 cites W3012289950 @default.
- W4385990911 cites W3034997246 @default.
- W4385990911 cites W3081251978 @default.
- W4385990911 cites W3083262573 @default.
- W4385990911 cites W3096609285 @default.
- W4385990911 cites W3097722521 @default.
- W4385990911 cites W3113753692 @default.
- W4385990911 cites W3118722740 @default.
- W4385990911 cites W3120055985 @default.
- W4385990911 cites W3158661000 @default.
- W4385990911 cites W3163021734 @default.
- W4385990911 cites W3172507542 @default.
- W4385990911 cites W3178925974 @default.
- W4385990911 cites W3190766843 @default.
- W4385990911 cites W3196203992 @default.
- W4385990911 cites W3201871940 @default.
- W4385990911 cites W3205155483 @default.
- W4385990911 cites W3217518891 @default.
- W4385990911 cites W4200099460 @default.
- W4385990911 cites W4221117907 @default.
- W4385990911 cites W4246722913 @default.
- W4385990911 cites W4281866774 @default.
- W4385990911 cites W4288042030 @default.
- W4385990911 cites W4295122681 @default.
- W4385990911 cites W4296467223 @default.
- W4385990911 cites W4306939332 @default.
- W4385990911 doi "https://doi.org/10.1007/978-3-031-41679-8_4" @default.
- W4385990911 hasPublicationYear "2023" @default.
- W4385990911 type Work @default.
- W4385990911 citedByCount "0" @default.
- W4385990911 crossrefType "book-chapter" @default.
- W4385990911 hasAuthorship W4385990911A5051437282 @default.
- W4385990911 hasAuthorship W4385990911A5051650277 @default.
- W4385990911 hasAuthorship W4385990911A5065666680 @default.
- W4385990911 hasAuthorship W4385990911A5073619925 @default.
- W4385990911 hasAuthorship W4385990911A5086894159 @default.
- W4385990911 hasConcept C119857082 @default.
- W4385990911 hasConcept C121332964 @default.
- W4385990911 hasConcept C124101348 @default.
- W4385990911 hasConcept C136389625 @default.
- W4385990911 hasConcept C153180895 @default.
- W4385990911 hasConcept C154945302 @default.
- W4385990911 hasConcept C165801399 @default.
- W4385990911 hasConcept C2776145971 @default.
- W4385990911 hasConcept C41008148 @default.