SOTAVerified

document understanding

Document understanding involves document classification, layout analysis, information extraction, and DocQA.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–125 of 309 papers

TitleStatusHype
3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document UnderstandingCode0
MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document UnderstandingCode0
Learned Compression for Compressed LearningCode0
LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document UnderstandingCode0
Long-Range Transformer Architectures for Document UnderstandingCode0
M-DocSum: Do LVLMs Genuinely Comprehend Interleaved Image-Text in Document Summarization?Code0
DocMIA: Document-Level Membership Inference Attacks against DocVQA ModelsCode0
Is ChatGPT A Good Keyphrase Generator? A Preliminary StudyCode0
KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document UnderstandingCode0
Evaluating Menu OCR and Translation: A Benchmark for Aligning Human and Automated Evaluations in Large Vision-Language ModelsCode0
A Survey of Deep Learning Approaches for OCR and Document UnderstandingCode0
Knowing Where and What: Unified Word Block Pretraining for Document UnderstandingCode0
Blockwise Self-Attention for Long Document UnderstandingCode0
Information Extraction from Visually Rich Documents Using Directed Weighted Graph Neural NetworkCode0
Information Redundancy and Biases in Public Document Information Extraction BenchmarksCode0
SFDLA: Source-Free Document Layout AnalysisCode0
LayoutLLM: Layout Instruction Tuning with Large Language Models for Document UnderstandingCode0
Deeper Clinical Document Understanding Using Relation ExtractionCode0
Hypergraph based Understanding for Document Semantic Entity RecognitionCode0
Improving Clinical Document Understanding on COVID-19 Research with Spark NLPCode0
Bidirectional Context-Aware Hierarchical Attention Network for Document UnderstandingCode0
BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata ExtractionCode0
HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in HanjaCode0
Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document ParsingCode0
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document UnderstandingCode0
Show:102550
← PrevPage 5 of 13Next →

No leaderboard results yet.