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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/opendatalab/DocLayout-YOLO
공식 코드https://github.com/opengvlab/internvl
공식 코드https://github.com/oryx-mllm/oryx
공식 코드Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
https://github.com/pd162/roi-matching
공식 코드Class-Agnostic Region-of-Interest Matching in Document Images
https://github.com/pengfei-hu/mtd
공식 코드Multimodal Tree Decoder for Table of Contents Extraction in Document Images
https://github.com/recitalai/skim-attention
공식 코드https://github.com/rubenpt91/MP-DocVQA-Framework
공식 코드https://github.com/s3setewe/sfdla-dladapter
공식 코드https://github.com/salesforce/qvr-simpledlm
공식 코드Value Retrieval with Arbitrary Queries for Form-like Documents
https://github.com/scb-10x/typhoon2-audio
공식 코드Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models
https://github.com/seif-lat/bias-study-funsd-sroie
공식 코드Information Redundancy and Biases in Public Document Information Extraction Benchmarks
https://github.com/seyoungsong/hanja-platform
공식 코드HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in Hanja
https://github.com/shirapp/coreference-based-ontology-building
공식 코드https://github.com/showlab/VisInContext
공식 코드Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning
https://github.com/shulk97/daniel
공식 코드https://github.com/stanford-oval/Lemonade
공식 코드LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World
https://github.com/tahmedge/WSL-DS-COLING-2020
공식 코드https://github.com/taosong2019/utel
공식 코드Knowing Where and What: Unified Word Block Pretraining for Document Understanding
https://github.com/thejaelal/lineformer
공식 코드LineFormer: Rethinking Line Chart Data Extraction as Instance Segmentation
https://github.com/thibaultdouzon/long-range-document-transformer
공식 코드Long-Range Transformer Architectures for Document Understanding
https://github.com/thudm/glm-4.1v-thinking
공식 코드GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
https://github.com/thunlp/llmxmapreduce
공식 코드LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models
https://github.com/tools-only/Evasion-Attack-against-LDA-Model
공식 코드EvaLDA: Efficient Evasion Attacks Towards Latent Dirichlet Allocation
https://github.com/uobinxiao/SparseTableDet
공식 코드https://github.com/veason-silverbullet/vitlp
공식 코드Visually Guided Generative Text-Layout Pre-training for Document Intelligence
https://github.com/wendywangwwt/zero-shot-complex-question-answering-on-long-scientific-documents
공식 코드Zero-Shot Complex Question-Answering on Long Scientific Documents
https://github.com/wenwenyu/MASTER-pytorch
공식 코드https://github.com/whlscut/DocLayLLM
공식 코드https://github.com/x-lance/weblm
공식 코드Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding
https://github.com/x-plug/mplug-docowl
공식 코드mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
https://github.com/xptree/BlockBERT
공식 코드https://github.com/yh-hust/pdf-wukong
공식 코드PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling
https://github.com/yuliang-liu/monkey
공식 코드TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document
https://github.com/zzr8066/graphdoc
공식 코드Multimodal Pre-training Based on Graph Attention Network for Document Understanding
https://github.com/2023-MindSpore-1/ms-code-2/tree/main/OCRNet
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.