Cite
Notes
Only stored in your browser.
Attribution
MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding
arXiv 2025
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
what-is-wrong-with-scene-text-recognition-1
from 2 papers
Atsuyuki Miyai
Dongyoon Han
Geewook Kim
Hikaru Ikuta
Hwalsuk Lee
Junyeop Lee
Kazuki Egashira
Kiyoharu Aizawa
Sangdoo Yun
Seong Joon Oh