Multi-modal Retrieval

Multi-Modal Retrieval is a retrieval paradigm that enables the joint processing and alignment of information from two or more distinct modalities—such as text, image, audio, and video—to achieve content-based querying and matching across heterogeneous data sources.

686

Publications

38.6K

Citations

2K

Authors

515

Institutions

Publications per year

2017–2026

465

Authors

2K

  1. LN
    Liqiang Nie

    Shandong University, China

    15 publications · 1.1K citations

    15

    h-index

  2. LZ
    Lei Zhu

    Shandong Normal University, China

    15 publications · 876 citations

    15

    h-index

  3. HZ
    Huaxiang Zhang

    Shandong Normal University, China

    16 publications · 726 citations

    15

    h-index

  4. HT
    Heng Tao Shen

    University of Electronic Science and Technology of China, China

    14 publications · 2K citations

    14

    h-index

  5. YY
    Yang Yang

    University of Electronic Science and Technology of China, China

    14 publications · 1.7K citations

    14

    h-index

1–5 of 2K

Venues

  1. IEEE Transactions on Multimedia

    34 publications · 2.2K citations

    27

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 22 publications · 2.3K citations

    20

    h-index

  3. IEEE Transactions on Image Processing

    22 publications · 2.4K citations

    20

    h-index

  4. arXiv (Cornell University)

    Repository · 37 publications · 2.3K citations

    18

    h-index

  5. 15

    h-index

1–5