73 citations · 85 across the 12 of their papers we have counts for
13 papers
Manga109-v2026: Revisiting Manga109 Annotations for Modern Manga Understanding
Jeonghun Baek, Atsuyuki Miyai, Shota Onohara +2
Manga is a culturally distinctive multimodal medium and one of the most influential forms of Japanese popular culture. As AI systems increasingly target manga understanding, OCR, a…
Beyond Bilingual Transfer: Multilingual Code-Switching in Instruction Tuning
Shunta Asano, Jeonghun Baek, Toshihiko Yamasaki
Recent studies have shown that code-switching data (CSD), in which multiple languages are mixed within the same context, can improve cross-lingual transfer and multilingual alignme…
JMMMU-Pro: Image-based Japanese Multi-discipline Multimodal Understanding Benchmark via Vibe Benchmark Construction
Atsuyuki Miyai, Shota Onohara, Jeonghun Baek +1
This paper introduces JMMMU-Pro, an image-based Japanese Multi-discipline Multimodal Understanding Benchmark, and Vibe Benchmark Construction, a scalable construction method. Follo…
MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding
Jeonghun Baek, Kazuki Egashira, Shota Onohara +4
Manga, or Japanese comics, is a richly multimodal narrative form that blends images and text in complex ways. Teaching large multimodal models (LMMs) to understand such narratives…
Harnessing PDF Data for Improving Japanese Large Multimodal Models
Jeonghun Baek, Akiko Aizawa, Kiyoharu Aizawa
Large Multimodal Models (LMMs) have demonstrated strong performance in English, but their effectiveness in Japanese remains limited due to the lack of high-quality training data. C…
JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation
Shota Onohara, Atsuyuki Miyai, Yuki Imajuku +5
Accelerating research on Large Multimodal Models (LMMs) in non-English languages is crucial for enhancing user experiences across broader populations. In this paper, we introduce J…
Cross-Lingual Learning in Multilingual Scene Text Recognition
Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa
In this paper, we investigate cross-lingual learning (CLL) for multilingual scene text recognition (STR). CLL transfers knowledge from one language to another. We aim to find the c…
COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa
Recognizing irregular texts has been a challenging topic in text recognition. To encourage research on this topic, we provide a novel comic onomatopoeia dataset (COO), which consis…
What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa
Scene text recognition (STR) task has a common practice: All state-of-the-art STR models are trained on large synthetic data. In contrast to this practice, training STR models only…
Character Region Attention For Text Spotting
Youngmin Baek, Seung Shin, Jeonghun Baek +4
A scene text spotter is composed of text detection and recognition modules. Many studies have been conducted to unify these modules into an end-to-end trainable model to achieve be…
CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks
Youngmin Baek, Daehyun Nam, Sungrae Park +5
Despite the recent success of text detection and recognition methods, existing evaluation metrics fail to provide a fair and reliable comparison among those methods. In addition, t…
On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention
Junyeop Lee, Sungrae Park, Jeonghun Baek +3
Scene text recognition (STR) is the task of recognizing character sequences in natural scenes. While there have been great advances in STR methods, current methods still fail to re…
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
Jeonghun Baek, Geewook Kim, Junyeop Lee +5
Many new proposals for scene text recognition (STR) models have been introduced in recent years. While each claim to have pushed the boundary of the technology, a holistic and fair…