Concepedia

Multi-modal Document Understanding

Multi-Modal Document Understanding is a document analysis framework that integrates and interprets complementary information from multiple data modalities—such as textual, visual, and layout features—within a single document to achieve a comprehensive, context-aware representation of its content and structure.

33

Publications

2.3K

Citations

174

Authors

35

Institutions

Publications per year

2017–2026

30

Parents

Publications

33

LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding

Yang Xu, Yiheng Xu, Tengchao Lv et al. · 2021 · 438 citations · Full text

, , +16

DocFormer: End-to-End Transformer for Document Understanding

Srikar Appalaraju, Bhavan Jasani, Bhargava Urala Kota et al. · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 292 citations

, , +16

Multiple-documents literacy: Strategic processing, source awareness, and argumentation when reading multiple conflicting documents

Øistein Anmarkrud, Ivar Bråten, Helge I. Strømsø · Learning and Individual Differences · 2013 · 227 citations

, , +15

DocBank: A Benchmark Dataset for Document Layout Analysis

Minghao Li, Yiheng Xu, Lei Cui et al. · 2020 · 186 citations · Full text

, , +15

StrucTexT: Structured Text Understanding with Multi-Modal Transformers

Yulin Li, Yuxi Qian, Yuechen Yu et al. · 2021 · 118 citations

, , +15

1–5 of 33

Authors

174

  1. FW
    Furu Wei

    Microsoft Research Asia (China), China

    7 publications · 792 citations

    7

    h-index

  2. YX
    Yiheng Xu

    Microsoft Research Asia (China), China

    7 publications · 792 citations

    7

    h-index

  3. GW
    Guoxin Wang

    Beijing Institute of Technology, China

    4 publications · 644 citations

    4

    h-index

  4. CZ
    Cha Zhang

    Microsoft (United States), United States

    4 publications · 644 citations

    4

    h-index

  5. LC
    Lei Cui

    Northwest University, China

    3 publications · 267 citations

    3

    h-index

1–5 of 174

Institutions

35

  1. Microsoft Research (United Kingdom)

    Cambridge, United Kingdom

    3 h-index

    22 publications

    1K citations

  2. Microsoft Research Asia (China)

    Beijing, China

    3 h-index

    14 publications

    3.6K citations

  3. University of Science and Technology of China

    Hefei, China

    3 h-index

    7 publications

    209 citations

  4. Microsoft (United States)

    Redmond, United States

    2 h-index

    12 publications

    2.5K citations

  5. Shanghai Jiao Tong University

    Shanghai, China

    2 h-index

    3 publications

    194 citations

  6. Baidu (China)

    Beijing, China

    2 h-index

    16 publications

    1.1K citations

  7. Beihang University

    Beijing, China

    2 h-index

    4 publications

    416 citations

  8. University of Chinese Academy of Sciences

    Beijing, China

    2 h-index

    3 publications

    105 citations

1–8 of 35

Venues

  1. arXiv (Cornell University)

    Repository · 9 publications · 236 citations

    9

    h-index

  2. Proceedings of the 30th ACM International Conference on Multimedia

    Conference · 2 publications · 47 citations

    2

    h-index

  3. Pattern Recognition

    2 publications · 86 citations

    2

    h-index

  4. 1

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 1 publications · 45 citations

    1

    h-index

1–5