Image Captioning

Image Captioning is a natural language generation task that involves generating a coherent and contextually accurate textual description of the visual content in an image, distinguished from other language generation tasks by its reliance on multimodal input grounded in computer vision.

1.6K

Publications

206.6K

Citations

4.4K

Authors

878

Institutions

Publications per year

2017–2026

1.4K

Authors

4.4K

  1. HZ
    Hanwang Zhang

    Nanyang Technological University, Singapore

    23 publications · 5.1K citations

    21

    h-index

  2. XH
    Xiaodong He

    Microsoft (United States), United States

    21 publications · 9K citations

    20

    h-index

  3. DP
    Devi Parikh

    Georgia Institute of Technology, United States

    18 publications · 33.3K citations

    18

    h-index

  4. ZG
    Zhe Gan

    Microsoft Research (United Kingdom), United Kingdom

    19 publications · 3.2K citations

    17

    h-index

  5. JL
    Jiebo Luo

    University of Rochester, United States

    19 publications · 3K citations

    16

    h-index

1–5 of 4.4K

Venues

  1. arXiv (Cornell University)

    Repository · 312 publications · 45.4K citations

    75

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 62 publications · 5.9K citations

    35

    h-index

  3. IEEE Transactions on Multimedia

    37 publications · 3.1K citations

    28

    h-index

  4. Neurocomputing

    31 publications · 1.6K citations

    23

    h-index

  5. IEEE Access

    34 publications · 1.1K citations

    21

    h-index

1–5