R.R.C. Robust Reading Competition
  • Home (current)
  • Challenges
    • DocVQA2020-23
    • ReST2023
    • SVRD2023
    • DSText2023
    • DUDE 😎2023
    • NewsVideoQA2023
    • RoadText2023
    • DocILE2023
    • HierText2022
    • Out of Vocabulary2022
    • ST-VQA2019
    • MLT2019
    • LSVT2019
    • ArT2019
    • SROIE2019
    • ReCTS2019
    • COCO-Text2017
    • DeTEXT2017
    • DOST2017
    • FSNS2017
    • MLT2017
    • IEHHR2017
    • Incidental Scene Text2015
    • Text in Videos2013-2015
    • Focused Scene Text2013-2015
    • Born-Digital Images (Web and Email)2011-2015
  • Register
    SROIE 2019
  • Overview
  • Tasks
  • Downloads
  • Results
  • My Methods
  • Organizers
  • Home
  • SROIE
  • Results
  • Task 2 - Scanned Receipt OCR
  • Method: BiLstmCtcIgnoreSpaces-Segment
  • Task 2 - Scanned Receipt OCR - Method: BiLstmCtcIgnoreSpaces-Segment
  • Method info
  • Samples list
  • Per sample details

method: BiLstmCtcIgnoreSpaces-Segment2019-04-22

Authors: Shen, He, Meng, Wu

Description: The Backbone is CRNN(Convolutional Recurrent Neural Network) + attention + ctc;
Label Generation: Ignore Spaces & add a new label to predict spaces

A. Gupta, A. Vedaldi, and A. Zisserman. Synthetic Data for Text Localisation in Natural Images. In CVPR, pages 2315–2324, 2016. C. Y. Lee and S. Osindero. Recursive Recurrent Nets with Attention Modeling for OCR in the Wild. In CVPR, pages 2231–2239, 2016.