Papers with Code 아카이브

Document AI

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

1

보존된 평가 기록

1

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/microsoft/unilm/tree/master/layoutxlm

공식 코드

LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding

https://github.com/microsoft/unilm/tree/master/markuplm

공식 코드

MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding

https://github.com/microsoft/unilm/tree/master/xdoc

공식 코드

XDoc: Unified Pre-training for Cross-Format Document Understanding

https://github.com/mmrezaee/VRTM

공식 코드

A Discrete Variational Recurrent Topic Model without the Reparametrization Trick

https://github.com/mv96/mm_extraction

공식 코드

Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)

https://github.com/mysong7nlper/chatgpt_as_keyphrase_generator

공식 코드

Is ChatGPT A Good Keyphrase Generator? A Preliminary Study

https://github.com/naver-ai/cream

공식 코드

Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models

https://github.com/naver-ai/elva

공식 코드

On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning

https://github.com/neeleshkshukla/dosa

공식 코드

DoSA : A System to Accelerate Annotations on Business Documents with Human-in-the-Loop

https://github.com/nttmdlab-nlp/instructdoc

공식 코드

InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions

https://github.com/opendatalab/DocLayout-YOLO

공식 코드

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

https://github.com/opengvlab/internvl

공식 코드

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

https://github.com/oryx-mllm/oryx

공식 코드

Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution

https://github.com/pd162/roi-matching

공식 코드

Class-Agnostic Region-of-Interest Matching in Document Images

https://github.com/pengfei-hu/mtd

공식 코드

Multimodal Tree Decoder for Table of Contents Extraction in Document Images

https://github.com/pengyu965/chartdete

공식 코드

Context-Aware Chart Element Detection

https://github.com/recitalai/skim-attention

공식 코드

Skim-Attention: Learning to Focus via Document Layout

https://github.com/rubenpt91/MP-DocVQA-Framework

공식 코드

Document Understanding Dataset and Evaluation (DUDE)

https://github.com/s3setewe/sfdla-dladapter

공식 코드

SFDLA: Source-Free Document Layout Analysis

https://github.com/salesforce/qvr-simpledlm

공식 코드

Value Retrieval with Arbitrary Queries for Form-like Documents

https://github.com/samakos/document-ai-

공식 코드

Document AI: A Comparative Study of Transformer-Based, Graph-Based Models, and Convolutional Neural Networks For Document Layout Analysis

https://github.com/scb-10x/typhoon2-audio

공식 코드

Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models

https://github.com/seif-lat/bias-study-funsd-sroie

공식 코드

Information Redundancy and Biases in Public Document Information Extraction Benchmarks

https://github.com/seyoungsong/hanja-platform

공식 코드

HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in Hanja

https://github.com/shirapp/coreference-based-ontology-building

공식 코드

Data-driven Coreference-based Ontology Building

https://github.com/showlab/VisInContext

공식 코드

Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning

https://github.com/shulk97/daniel

공식 코드

DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents

https://github.com/stanford-oval/Lemonade

공식 코드

LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World

https://github.com/tahmedge/WSL-DS-COLING-2020

공식 코드

WSL-DS: Weakly Supervised Learning with Distant Supervision for Query Focused Multi-Document Abstractive Summarization

https://github.com/taosong2019/utel

공식 코드

Knowing Where and What: Unified Word Block Pretraining for Document Understanding

https://github.com/thejaelal/lineformer

공식 코드

LineFormer: Rethinking Line Chart Data Extraction as Instance Segmentation

https://github.com/thibaultdouzon/long-range-document-transformer

공식 코드

Long-Range Transformer Architectures for Document Understanding

https://github.com/thudm/glm-4.1v-thinking

공식 코드

GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

https://github.com/thunlp/llmxmapreduce

공식 코드

LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models

https://github.com/tools-only/Evasion-Attack-against-LDA-Model

공식 코드

EvaLDA: Efficient Evasion Attacks Towards Latent Dirichlet Allocation

https://github.com/uobinxiao/SparseTableDet

공식 코드

Table Detection for Visually Rich Document Images

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.