English
Related papers

Related papers: ICDAR 2023 Competition on Robust Layout Segmentati…

200 papers

Visual Document Understanding (VDU) systems have achieved strong performance in information extraction by integrating textual, layout, and visual signals. However, their robustness under realistic adversarial perturbations remains…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Dong Nguyen Tien , Dung D. Le

The proliferation of long-form documents presents a fundamental challenge to information retrieval (IR), as their length, dispersed evidence, and complex structures demand specialized methods beyond standard passage-level techniques. This…

Information Retrieval · Computer Science 2025-10-28 Minghan Li , Miyang Luo , Tianrui Lv , Yishuai Zhang , Siqi Zhao , Ercong Nie , Guodong Zhou

Document layout analysis aims to detect and categorize structural elements (e.g., titles, tables, figures) in scanned or digital documents. Popular methods often rely on high-quality Optical Character Recognition (OCR) to merge visual…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Fuyuan Liu , Dianyu Yu , He Ren , Nayu Liu , Xiaomian Kang , Delai Qiu , Fa Zhang , Genpeng Zhen , Shengping Liu , Jiaen Liang , Wei Huang , Yining Wang , Junnan Zhu

Understanding and extracting of information from large documents, such as business opportunities, academic articles, medical documents and technical reports, poses challenges not present in short documents. Such large documents may be…

Computation and Language · Computer Science 2019-10-10 Muhammad Mahbubur Rahman , Tim Finin

The ability to understand and answer questions over documents can be useful in many business and practical applications. However, documents often contain lengthy and diverse multimodal contents such as texts, figures, and tables, which are…

Computation and Language · Computer Science 2024-11-12 Yew Ken Chia , Liying Cheng , Hou Pong Chan , Chaoqun Liu , Maojia Song , Sharifah Mahani Aljunied , Soujanya Poria , Lidong Bing

This paper introduces the DocILE benchmark with the largest dataset of business documents for the tasks of Key Information Localization and Extraction and Line Item Recognition. It contains 6.7k annotated business documents, 100k…

This paper defines and explores the design space for information extraction (IE) from layout-rich documents using large language models (LLMs). The three core challenges of layout-aware IE with LLMs are 1) data structuring, 2) model…

Computation and Language · Computer Science 2026-02-04 Gaye Colakoglu , Gürkan Solmaz , Jonathan Fürst

Despite several successes in document understanding, the practical task for long document understanding is largely under-explored due to several challenges in computation and how to efficiently absorb long multimodal input. Most current…

Computation and Language · Computer Science 2022-08-18 Hai Pham , Guoxin Wang , Yijuan Lu , Dinei Florencio , Cha Zhang

Information Retrieval (IR) methods aim to identify documents relevant to a query, which have been widely applied in various natural language tasks. However, existing approaches typically consider only the textual content within documents,…

Computation and Language · Computer Science 2026-01-26 Jaewoo Lee , Joonho Ko , Jinheon Baek , Soyeong Jeong , Sung Ju Hwang

Extracting key information from documents represents a large portion of business workloads and therefore offers a high potential for efficiency improvements and process automation. With recent advances in Deep Learning, a plethora of Deep…

Information Retrieval · Computer Science 2025-07-21 Alexander Michael Rombach , Peter Fettke

Academic documents are packed with texts, equations, tables, and figures, requiring comprehensive understanding for accurate Optical Character Recognition (OCR). While end-to-end OCR methods offer improved accuracy over layout-based…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Yu Sun , Dongzhan Zhou , Chen Lin , Conghui He , Wanli Ouyang , Han-Sen Zhong

Text image super-resolution is a challenging yet open research problem in the computer vision community. In particular, low-resolution images hamper the performance of typical optical character recognition (OCR) systems. In this article, we…

Computer Vision and Pattern Recognition · Computer Science 2015-06-09 Chao Dong , Ximei Zhu , Yubin Deng , Chen Change Loy , Yu Qiao

One major drawback of state of the art Neural Networks (NN)-based approaches for document classification purposes is the large number of training samples required to obtain an efficient classification. The minimum required number is around…

Computer Vision and Pattern Recognition · Computer Science 2020-07-16 Joris Voerman , Aurelie Joseph , Mickael Coustaty , Vincent Poulain d Andecy , Jean-Marc Ogier

Automating the annotation of scanned documents is challenging, requiring a balance between computational efficiency and accuracy. DocParseNet addresses this by combining deep learning and multi-modal learning to process both text and visual…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Ahmad Mohammadshirazi , Ali Nosrati Firoozsalari , Mengxi Zhou , Dheeraj Kulshrestha , Rajiv Ramnath

The proliferation of multimodal Large Language Models has significantly advanced the ability to analyze and understand complex data inputs from different modalities. However, the processing of long documents remains under-explored, largely…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Goeric Huybrechts , Srikanth Ronanki , Sai Muralidhar Jayanthi , Jack Fitzgerald , Srinivasan Veeravanallur

Differentiable Search Index is a recently proposed paradigm for document retrieval, that encodes information about a corpus of documents within the parameters of a neural network and directly maps queries to corresponding documents. These…

Information Retrieval · Computer Science 2024-08-20 Varsha Kishore , Chao Wan , Justin Lovelace , Yoav Artzi , Kilian Q. Weinberger

Binarization of digital documents is the task of classifying each pixel in an image of the document as belonging to the background (parchment/paper) or foreground (text/ink). Historical documents are often subjected to degradations, that…

Machine Learning · Statistics 2018-05-18 Kalyan Ram Ayyalasomayajula , Filip Malmberg , Anders Brun

Document parsing has recently advanced with multimodal large language models (MLLMs) that directly map document images to structured outputs. Traditional cascaded pipelines depend on precise layout analysis and often fail under casually…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Gengluo Li , Pengyuan Lyu , Chengquan Zhang , Huawen Shen , Liang Wu , Xingyu Wan , Gangyan Zeng , Han Hu , Can Ma , Yu Zhou

Our analysis of the NeurIPS 2023 large language model (LLM) fine-tuning competition revealed the following trend: top-performing models exhibit significant overfitting on benchmark datasets, mirroring the broader issue of benchmark…

Automatically recognizing the layout of handwritten documents is an important step towards useful extraction of information from those documents. The most common application is to feed downstream applications such as automatic text…

Computer Vision and Pattern Recognition · Computer Science 2021-06-23 Lorenzo Quirós , Enrique Vidal