Papers with Code 아카이브
Document AI
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/danyang-liu/KRED
공식 코드KRED: Knowledge-Aware Document Representation for News Recommendations
https://github.com/daod/inters
공식 코드INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning
https://github.com/dcgm/biblio-dataset
공식 코드BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction
https://github.com/dengc2023/longdocurl
공식 코드https://github.com/emanuelevivoli/awesome-comics-understanding
공식 코드One missing piece in Vision and Language: A Survey on Comics Understanding
https://github.com/flagopen/flagembedding
공식 코드https://github.com/fuxiaoliu/documentclip
공식 코드DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents
https://github.com/giannisnik/mpad
공식 코드Message Passing Attention Networks for Document Understanding
https://github.com/gitwzl/motbench
공식 코드https://github.com/guoxy25/Ocean-OCR
공식 코드Ocean-OCR: Towards General OCR Application via a Vision-Language Model
https://github.com/harrytea/tgdoc
공식 코드Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs
https://github.com/henryk-mustroph/first_version_qmsaia
공식 코드Design of a Quality Management System based on the EU Artificial Intelligence Act
https://github.com/herobd/dessurt
공식 코드End-to-end Document Recognition and Understanding with Dessurt
https://github.com/hikopensource/davar-lab-ocr
공식 코드TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
https://github.com/hint-lab/doctrack
공식 코드https://github.com/ibm-aur-nlp/PubLayNet
공식 코드https://github.com/ibm-aur-nlp/PubTabNet
공식 코드https://github.com/jpwang/lilt
공식 코드https://github.com/kasuba-badri-vishal/dhrishtikon
공식 코드DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images
https://github.com/khanhnguyen21006/mia_docvqa
공식 코드DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
https://github.com/laytextllm/laytextllm
공식 코드https://github.com/leitro/machineunlearning-docclassification
공식 코드https://github.com/leitro/selfattnscoring-mpdocvqa
공식 코드Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism
https://github.com/leloykun/mmfm-challenge
공식 코드Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report
https://github.com/line-kite/graphlayoutlm
공식 코드Enhancing Visually-Rich Document Understanding via Layout Structure Modeling
https://github.com/maehcm/do-good
공식 코드Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models
https://github.com/mbzuai-oryx/AIN
공식 코드https://github.com/mbzuai-oryx/CAMEL-Bench
공식 코드https://github.com/mbzuai-oryx/arb
공식 코드https://github.com/metricsdi/dimetrics
공식 코드Document Intelligence Metrics for Visually Rich Document Evaluation
https://github.com/microsoft/i-code
공식 코드Unifying Vision, Text, and Layout for Universal Document Processing
https://github.com/microsoft/udop
공식 코드Unifying Vision, Text, and Layout for Universal Document Processing
https://github.com/microsoft/unilm
공식 코드LayoutLM: Pre-training of Text and Layout for Document Image Understanding
https://github.com/microsoft/unilm/tree/master/dit
공식 코드DiT: Self-supervised Pre-training for Document Image Transformer
https://github.com/microsoft/unilm/tree/master/layoutlmv3
공식 코드LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.