Papers with Code 아카이브
Document Image Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 8
- 보존된 평가 기록
- 49
Document image classification is the task of classifying documents based on images of their contents.
<span style="color:grey; opacity: 0.6">( Image credit: Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
DoPTA: Improving Document Layout Analysis using Patch-Text Alignment
DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classification
DistilDoc: Knowledge Distillation for Visually-Rich Document Applications
Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting
CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification
LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding
Automatic Recognition of Learning Resource Category in a Digital Library
SUT: a new multi-purpose synthetic dataset for Farsi document image analysis
A Multi-Modal Multilingual Benchmark for Document Image Classification
GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification
LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding
EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification
Evaluating Adversarial Robustness on Document Image Classification
Context-Aware Classification of Legal Document Pages
StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
Multimodal Side-Tuning for Document Classification
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
DocXClassifier: High Performance Explainable Deep Network for Document Image Classification
DiT: Self-supervised Pre-training for Document Image Transformer
LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
OCR-free Document Understanding Transformer
Document AI: Benchmarks, Models and Applications
Domain Agnostic Few-Shot Learning For Document Intelligence
Efficient Document Image Classification Using Region-Based Graph Neural Network
DocFormer: End-to-End Transformer for Document Understanding
BEiT: BERT Pre-Training of Image Transformers
Toward Automatic Interpretation of 3D Plots
StructuralLM: Structural Pre-training for Form Understanding
LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
Revisiting ResNets: Improved Training and Scaling Strategies
Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
Training data-efficient image transformers & distillation through attention
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.