no code implementations • 1 May 2024 • Yamato Okamoto, Youngmin Baek, Geewook Kim, Ryota Nakao, Donghyun Kim, Moon Bin Yim, Seunghyun Park, Bado Lee
CREPE's abilities including OCR and semantic parsing not only mitigate error propagation issues in existing OCR-dependent methods, it also significantly enhance the functionality of sequence generation models, ushering in a new era for document understanding studies.
document understanding Optical Character Recognition (OCR) +3
no code implementations • 26 Mar 2024 • rintaro yanagi, Yamato Okamoto, Shuhei Yokoo, Shin'ichi Satoh
From the experimental results focusing on segment-level and video-level situations, we can see that three effects: "Segment-level VCD in short video-sharing services is more difficult than those in general video-sharing services", "Video-level VCD in short video-sharing services is easier than those in general video-sharing services", "The video alignment component mainly suppress the detection performance in short video-sharing services".
no code implementations • 7 Nov 2023 • Yamato Okamoto, Osada Genki, Iu Yahiro, Rintaro Hasegawa, Peifei Zhu, Hirokatsu Kataoka
In recent years, document processing has flourished and brought numerous benefits.
no code implementations • 3 Oct 2023 • Yamato Okamoto, Haruto Toyonaga, Yoshihisa Ijiri, Hirokatsu Kataoka
Digital archiving is becoming widespread owing to its effectiveness in protecting valuable books and providing knowledge to many people electronically.