Papers with Code 아카이브
document understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
Document understanding involves document classification, layout analysis, information extraction, and DocQA.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API
ProtoNER: Few shot Incremental Learning for Named Entity Recognition using Prototypical Networks
Finding Pragmatic Differences Between Disciplines
Document Understanding for Healthcare Referrals
SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap
KOSMOS-2.5: A Multimodal Literate Model
Long-Range Transformer Architectures for Document Understanding
GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification
Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration
Vision Grid Transformer for Document Layout Analysis
Enhancing Visually-Rich Document Understanding via Layout Structure Modeling
Workshop on Document Intelligence Understanding
MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary
A Survey and Approach to Chart Classification
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
DocumentNet: Bridging the Data Gap in Document Pre-Training
DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents
Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models
DocFormerv2: Local Features for Document Understanding
LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding
Table Detection for Visually Rich Document Images
PaLI-X: On Scaling up a Multilingual Vision and Language Model
AWESOME: GPU Memory-constrained Long Document Summarization using Memory Mechanism and Global Salient Content
Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
DUBLIN -- Document Understanding By Language-Image Network
Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding
DLUE: Benchmarking Document Language Understanding
Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding
Document Understanding Dataset and Evaluation (DUDE)
M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis
Two to Five Truths in Non-Negative Matrix Factorization
FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction
Revisiting Table Detection Datasets for Visually Rich Documents
LineFormer: Rethinking Line Chart Data Extraction as Instance Segmentation
Information Redundancy and Biases in Public Document Information Extraction Benchmarks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.