Related papers: ICDAR 2023 Competition on Robust Layout Segmentati…
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…
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…
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…
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…
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…
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…
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…
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,…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…