Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Donut: Document Understanding Transformer without OCR


Nov 30, 2021
Geewook Kim, Teakgyu Hong, Moonbin Yim, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park

* 12 pages, 6 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

HoughCL: Finding Better Positive Pairs in Dense Self-supervised Learning


Nov 21, 2021
Yunsung Lee, Teakgyu Hong, Han-Cheol Cho, Junbum Cha, Seungryong Kim

* Accepted to ICML 2021 Workshop: Self-Supervised Learning for Reasoning and Perception 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents


Sep 10, 2021
Teakgyu Hong, Donghyun Kim, Mingi Ji, Wonseok Hwang, Daehyun Nam, Sungrae Park

* 13 pages, 9 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

BROS: A Layout-Aware Pre-trained Language Model for Understanding Documents


Aug 24, 2021
Teakgyu Hong, Donghyun Kim, Mingi Ji, Wonseok Hwang, Daehyun Nam, Sungrae Park

* 11 pages, 6 figures; corrected Table 10 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email