Cross-modal Retrieval

Cross-Modal Retrieval is a retrieval paradigm within multimedia information access that enables querying across heterogeneous modalities by leveraging the semantic relationships between distinct but aligned data types, such as text, images, audio, or video, to retrieve relevant instances from a target modality different from the query modality.

911

Publications

57.1K

Citations

2.4K

Authors

561

Institutions

Publications per year

2017–2026

746

Authors

2.4K

  1. XX
    Xing Xu

    University of Electronic Science and Technology of China, China

    30 publications · 2.8K citations

    23

    h-index

  2. HT
    Heng Tao Shen

    University of Electronic Science and Technology of China, China

    26 publications · 3.1K citations

    21

    h-index

  3. QT
    Qi Tian

    The University of Texas at San Antonio, United States

    20 publications · 873 citations

    18

    h-index

  4. YP
    Yuxin Peng

    Peking University, China

    21 publications · 2.1K citations

    17

    h-index

  5. YY
    Yang Yang

    University of Electronic Science and Technology of China, China

    18 publications · 2.5K citations

    17

    h-index

1–5 of 2.4K

Venues

  1. IEEE Transactions on Multimedia

    57 publications · 4K citations

    39

    h-index

  2. IEEE Transactions on Image Processing

    35 publications · 3.8K citations

    30

    h-index

  3. 26

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 24 publications · 2.1K citations

    22

    h-index

  5. arXiv (Cornell University)

    Repository · 50 publications · 2.3K citations

    22

    h-index

1–5