Related papers: \'Eclair -- Extracting Content and Layout with Int…
Forms are our gates to the web. They enable us to access the deep content of web sites. Automatic form understanding provides applications, ranging from crawlers over meta-search engines to service integrators, with a key to this content.…
Text recognition in the wild is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest vision and language processing are effective for scene text recognition. Yet, solving edit errors such as…
Document understanding refers to automatically extract, analyze and comprehend information from various types of digital documents, such as a web page. Existing Multi-model Large Language Models (MLLMs), including mPLUG-Owl, have…
Document structure extraction has been a widely researched area for decades with recent works performing it as a semantic segmentation task over document images using fully-convolution networks. Such methods are limited by image resolution…
Optical Character Recognition (OCR) systems have been widely used in various of application scenarios. Designing an OCR system is still a challenging task. In previous work, we proposed a practical ultra lightweight OCR system (PP-OCR) to…
Instruction tuning improves the performance of large language models (LLMs), but it heavily relies on high-quality training data. Recently, LLMs have been used to synthesize instruction data using seed question-answer (QA) pairs. However,…
Table extraction has long been a pervasive problem in financial services. This is more challenging in the image domain, where content is locked behind cumbersome pixel format. Luckily, advances in deep learning for image segmentation, OCR,…
Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large…
The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports. While page-level chunking and retrieval is a natural starting…
Searching is an important tool of information gathering, if information is in the form of picture than it play a major role to take quick action and easy to memorize. This is a human tendency to retain more picture than text. The complexity…
The ubiquity of smartphone cameras has led to more and more documents being captured by cameras rather than scanned. Unlike flatbed scanners, photographed documents are often folded and crumpled, resulting in large local variance in text…
Document information extraction tasks performed by humans create data consisting of a PDF or document image input, and extracted string outputs. This end-to-end data is naturally consumed and produced when performing the task because it is…
A challenge of the computer vision community is to understand the semantics of an image, in order to allow image reconstruction based on existing high-level features or to better analyze (semi-)labelled datasets. Towards addressing this…
Object-oriented reinforcement learning (OORL) is a promising way to improve the sample efficiency and generalization ability over standard RL. Recent works that try to solve OORL tasks without additional feature engineering mainly focus on…
Text-rich document understanding (TDU) requires comprehensive analysis of documents containing substantial textual content and complex layouts. While Multimodal Large Language Models (MLLMs) have achieved fast progress in this domain,…
Optical character recognition (OCR) technology has been widely used in various scenes, as shown in Figure 1. Designing a practical OCR system is still a meaningful but challenging task. In previous work, considering the efficiency and…
Despite the growing adoption of electronic health records, many processes still rely on paper documents, reflecting the heterogeneous real-world conditions in which healthcare is delivered. The manual transcription process is time-consuming…
Improving data quality in unstructured documents is a long-standing challenge. Unstructured data, especially in textual form, inherently lacks defined semantics, which poses significant challenges for effective processing and for ensuring…
Traditional OCR systems (OCR-1.0) are increasingly unable to meet people's usage due to the growing demand for intelligent processing of man-made optical characters. In this paper, we collectively refer to all artificial optical signals…
The purpose of this study is to explore the performance of Informed OCR or iOCR. iOCR was developed with a spell correction algorithm to fix errors introduced by conventional OCR for vote tabulation. The results found that the iOCR system…