相关论文: PdfTable: A Unified Toolkit for Deep Learning-Base…
The automatic recognition of tabular data in document images presents a significant challenge due to the diverse range of table styles and complex structures. Tables offer valuable content representation, enhancing the predictive…
PDF documents have the potential to provide trillions of novel, high-quality tokens for training language models. However, these documents come in a diversity of types with differing formats and visual layouts that pose a challenge when…
Extracting text objects from the PDF images is a challenging problem. The text data present in the PDF images contain certain useful information for automatic annotation, indexing etc. However variations of the text due to differences in…
Relevant information in documents is often summarized in tables, helping the reader to identify useful facts. Most benchmark datasets support either document layout analysis or table understanding, but lack in providing data to apply both…
We present an end-to-end, multimodal, fully convolutional network for extracting semantic structures from document images. We consider document semantic structure extraction as a pixel-wise segmentation task, and propose a unified model…
Metadata of scientific articles such as title, abstract, keywords or index terms, body text, conclusion, reference and others play a decisive role in collecting, managing and storing academic data in scientific databases, academic journals…
Document content extraction is a critical task in computer vision, underpinning the data needs of large language models (LLMs) and retrieval-augmented generation (RAG) systems. Despite recent progress, current document parsing methods have…
Diagrams play a crucial role in visually conveying complex relationships and processes within business documentation. Despite recent advances in Vision-Language Models (VLMs) for various image understanding tasks, accurately identifying and…
Tables are everywhere, from scientific journals, papers, websites, and newspapers all the way to items we buy at the supermarket. Detecting them is thus of utmost importance to automatically understanding the content of a document. The…
A crucial component in the curation of KB for a scientific domain (e.g., materials science, foods & nutrition, fuels) is information extraction from tables in the domain's published research articles. To facilitate research in this…
Unstructured documents like PDFs contain valuable structured information, but downstream systems require this data in reliable, standardized formats. LLMs are increasingly deployed to automate this extraction, making accuracy and…
Many documents, that we call templatized documents, are programmatically generated by populating fields in a visual template. Effective data extraction from these documents is crucial to supporting downstream analytical tasks. Current data…
Many solutions have been provided to extract bibliographic references from PDF papers. Machine learning, rule-based and regular expressions approaches were among the most used methods adopted in tools for addressing this task. This work…
This paper introduces CommonForms, a web-scale dataset for form field detection. It casts the problem of form field detection as object detection: given an image of a page, predict the location and type (Text Input, Choice Button,…
Automating information extraction from form-like documents at scale is a pressing need due to its potential impact on automating business workflows across many industries like financial services, insurance, and healthcare. The key challenge…
A central challenge in science is to understand how systems behaviors emerge from complex networks. This often requires aggregating, reusing, and integrating heterogeneous information. Supplementary spreadsheets to articles are a key data…
We address the extraction of mathematical statements and their proofs from scholarly PDF articles as a multimodal classification problem, utilizing text, font features, and bitmap image renderings of PDFs as distinct modalities. We propose…
Scientific research heavily depends on suitable datasets for method validation, but existing academic platforms with dataset management like PapersWithCode suffer from inefficiencies in their manual workflow. To overcome this bottleneck, we…
Table of contents (ToC) extraction aims to extract headings of different levels in documents to better understand the outline of the contents, which can be widely used for document understanding and information retrieval. Existing works…
Urban data support a wide range of applications across multiple disciplines. However, at the global scale, there is no unified platform for urban data discovery. As a result, researchers often have to manually search through websites or…