Related papers: PP-StructureV2: A Stronger Document Analysis Syste…
Recent efforts of multimodal Transformers have improved Visually Rich Document Understanding (VrDU) tasks via incorporating visual and textual information. However, existing approaches mainly focus on fine-grained elements such as words and…
Automatic table detection in PDF documents has achieved a great success but tabular data extraction are still challenging due to the integrity and noise issues in detected table areas. The accurate data extraction is extremely crucial in…
Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise document processing. We present a systematic framework that…
Accurately extracting structured content from PDFs is a critical first step for NLP over scientific papers. Recent work has improved extraction accuracy by incorporating elementary layout information, e.g., each token's 2D position on the…
Structure information is critical for understanding the semantics of text-rich images, such as documents, tables, and charts. Existing Multimodal Large Language Models (MLLMs) for Visual Document Understanding are equipped with text…
With the widespread use of mobile phones and scanners to photograph and upload documents, the need for extracting the information trapped in unstructured document images such as retail receipts, insurance claim forms and financial invoices…
Visual document understanding (VDU) is a challenging task that involves understanding documents across various modalities (text and image) and layouts (forms, tables, etc.). This study aims to enhance generalizability of small VDU models by…
Document parsing has garnered widespread attention as vision-language models (VLMs) advance OCR capabilities. However, the field remains fragmented across dozens of specialized models with varying strengths, forcing users to navigate…
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…
Understanding visually-rich business documents to extract structured data and automate business workflows has been receiving attention both in academia and industry. Although recent multi-modal language models have achieved impressive…
Tables present summarized and structured information to the reader, which makes table structure extraction an important part of document understanding applications. However, table structure identification is a hard problem not only because…
The current digital environment is characterized by the widespread presence of data, particularly unstructured data, which poses many issues in sectors including finance, healthcare, and education. Conventional techniques for data…
Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective…
The remarkable breakthroughs in point cloud representation learning have boosted their usage in real-world applications such as self-driving cars and virtual reality. However, these applications usually have an urgent requirement for not…
Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distillation is well recognized as the essential procedure in model…
Table structure recognition is necessary for a comprehensive understanding of documents. Tables in unstructured business documents are tough to parse due to the high diversity of layouts, varying alignments of contents, and the presence of…
Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities. However, effective aggregation of relevant…
Recent deep learning approaches in table detection achieved outstanding performance and proved to be effective in identifying document layouts. Currently, available table detection benchmarks have many limitations, including the lack of…
Accurate extraction of key information from 2D engineering drawings is crucial for high-precision manufacturing. Manual extraction is slow and labor-intensive, while traditional Optical Character Recognition (OCR) techniques often struggle…
Recent advances in multimodal learning have achieved remarkable success across diverse vision-language tasks. However, such progress heavily relies on large-scale image-text datasets, making training costly and inefficient. Prior efforts in…