Jeonghun Baek
7 papers · 2019–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (5) π Academic Marathon (6) π Renaissance Researcher (5) π Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(13)
π§
Keyword Pioneer
β
The Questioner
(2)
Conferences
ECCV (2)
ACL (1)
CVPR (1)
EACL (1)
ICCV (1)
NAACL (1)
Top co-authors
Keywords
large multimodal model
(2)
optical character recognition
(2)
scene text recognition
(2)
self-supervised learning
(1)
data augmentation
(1)
multimodal learning
(1)
instruction tuning
(1)
model comparison
(1)
label efficiency
(1)
synthetic datum
(1)
image-text pair
(1)
cultural knowledge
(1)
japanese language
(1)
multilingual multimodal
(1)
layout analysis
(1)
pdf extraction
(1)
benchmark evaluation
(1)
manga understanding
(1)
semi-supervised learning
(1)
visual question answering
(1)
Papers
MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding
EACL 2026
Harnessing PDF Data for Improving Japanese Large Multimodal Models
ACL 2025
JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation
NAACL 2025
COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
ECCV 2022
What if We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
CVPR 2021
Character Region Attention For Text Spotting
ECCV 2020
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
ICCV 2019