The paper introduces an all‑in‑one multilingual scene text recognizer called ScriptMoE, which uses a script‑aware mixture‑of‑experts architecture to handle 10 scripts and 229 languages. It is built on a new large‑scale synthetic dataset, TextMuSS‑10M, and evaluated on the TextMuSS‑Bench, achieving 82.06% accuracy—1.31% higher than the best baseline. When integrated into the PP‑OCRv5 pipeline, ScriptMoE raises the end‑to‑end multilingual F1 score from 65.71% to 80.89%, slightly surpassing the best vision‑language model while using far fewer parameters.
By Xingsong Ye, Yongkun Du, Jiaxin Zhang, Zhixian Li, Chong Sun, Chen Li, Jing Lyu, Lianwen Jin, Zhineng Chen
The paper introduces a data‑centric framework that enables end‑to‑end OCR for low‑resource scripts using only an unannotated text corpus and digital fonts, eliminating the need for manually annotated training images. A synthetic data engine generates realistic word, line, and page images with accurate script shaping, which are then used to train a YOLOv8 word detector and a convolutional recurrent recognizer via connectionist temporal classification. Applied to the Kashmiri Perso‑Arabic Nastaliq script, the system achieves a 0.39% character error rate on held‑out words and provides publicly released models, code, and a synthetic dataset of 285,864 text‑line images.
By Faizan Iqbal, Haq Nawaz Malik, Hafsah Pervaiz
Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering (TabVQA). While recent approaches predominantly rel...
arXiv:2512.10888v4 Announce Type: replace
Abstract: Table extraction (TE) is a key challenge in document understanding. Traditional approaches detect tables first, then recognize their structure. Rec...
By Brandon Smock, Maxim Sokolov, Libin Liang, Valerie Faucon-Morin, Amrit Ramesh, Tayyibah Khanam, Maury Courtland
The paper presents a local traditional OCR pipeline that can be iteratively fine‑tuned on both layout and appearance levels of complex historical Sanskrit manuscripts. By adapting to the specific manuscript distribution, the pipeline improves transcription accuracy across subsequent pages, reducing the need for costly human annotation. The authors apply the method to three manuscripts, release a dataset with detailed layout and Unicode annotations in PAGE‑XML format, and benchmark the results against leading multimodal large language models.
The paper presents a local traditional OCR pipeline that can be iteratively fine‑tuned on both layout and appearance levels of complex historical Sanskrit manuscripts. By adapting to the specific manuscript distribution, the pipeline reduces human annotation effort and improves transcription accuracy across subsequent pages. The authors apply this method to three manuscripts, release a dataset with detailed layout and Unicode annotations in PAGE‑XML format, and benchmark the pipeline against leading multimodal large language models.
By Kartik Chincholikar, Kaushik Gopalan, Mihir Hasabnis
arXiv:2609.14352v1 Announce Type: new
Abstract: AI-generated image detection has attracted increasing attention, but existing evaluations mainly focus on natural images, leaving AI-generated document...
By Zhangjie Fu, Jiazhen Yan, Yuanwen Chen, Xinquan Yu, Yanzhe Li, Hui Jiang, Lei Gao, Chenfu Bao
The paper introduces Synth-JDoc, a synthetic Japanese document image dataset created by rendering text with HTML and CSS to produce multi‑column layouts that include both vertical and horizontal writing styles. Images generated by text‑to‑image models are embedded to enhance visual realism, and noise and degradation filters are applied to improve robustness. Experiments show that fine‑tuning Large Vision Language Models on Synth‑JDoc yields superior performance on reading vertically written Japanese text compared to prior synthetic datasets.
By Keito Sasagawa, Shuhei Kurita, Daisuke Kawahara
arXiv:2609.17458v1 Announce Type: cross
Abstract: Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering...
By Jahanvi Rajput, Dhruv Kudale, Saikiran Kasturi, Utkarsh Verma, Ganesh Ramakrishnan
IndicDetect is a benchmark for evaluating AI‑generated text detection in Hindi, Telugu, and Tamil. It pairs curated human‑written texts with LLM‑generated counterparts across multiple domains and generators, testing detectors under domain shift, generator shift, and adversarial perturbation. The study shows that supervised neural detectors fail to generalize to unseen generators and attacks, with Hindi experiencing the greatest degradation, indicating that robustness—not peak accuracy—is the main weakness in Indic language detectors.
By Bhaskar Ganesh Devalla, Junchao Wu, Nilesh Dokuparthi, Greeshma Yaluru, Tatiana Muniz Rodriguez, Lidia S. Chao, Derek F. Wong
arXiv:2608. 12898v1 Announce Type: cross Abstract: Document parsing aims to transform unstructured documents into structured and machine-readable representations.
By Peng Cai, Zhaofan Zou, Shifa Liu, Yikun Wang, Jiawei Tang, Kaicheng Yang, Meng Tong, Zhongjiang He, Hao Sun
Ancient-Bench is a new benchmark for recognizing text on ancient Chinese artifacts, comprising 2,700 images that span 3,000 years of character evolution, nine artifact categories, and seven historical script forms. It introduces three annotation standards—symbol, character, and parsing standardization—to accommodate medium‑specific characteristics and enable consistent evaluation. Experiments show that current Vision‑Language Models and OCR specialists still struggle with variant characters, specialized symbols, and hallucination, indicating the task remains largely unsolved.
By Hiuyi Cheng, Nuo Xu, Yuyi Zhang, Xuhan Zheng, Wei Pan, Jing Zhang, Dezhi Peng, Minghui Liao, Yihua Teng, Jihao Wu, Haoyu Ren, Lianwen Jin