Concepedia

Multimodal Retrieval Models

Multimodal Retrieval Models is a retrieval framework that integrates and aligns information from multiple modalities—such as text, image, audio, and video—to enable cross-modal or multimodal query and document matching, distinguishing itself from unimodal retrieval models by leveraging heterogeneous data representations within a shared semantic space.

405

Publications

29K

Citations

2K

Authors

420

Institutions

Publications per year

2017–2026

270

Parents

Publications

405

Deep visual-semantic alignments for generating image descriptions

Andrej Karpathy, Li Fei-Fei · 2015 · 5K citations

, , +16

Deep Visual-Semantic Alignments for Generating Image Descriptions

Andrej Karpathy, Li Fei-Fei · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 1K citations

, , +16

Deep Fragment Embeddings for Bidirectional Image Sentence Mapping

Andrej Karpathy, Armand Joulin, Fei Fei F Li · arXiv (Cornell University) · 2014 · 726 citations · Full text

, , +16

Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)

Junhua Mao, Wei Xu, Yi Yang et al. · arXiv (Cornell University) · 2014 · 653 citations · Full text

, , +13

Cross-modal Retrieval with Correspondence Autoencoder

Fangxiang Feng, Xiaojie Wang, Ruifan Li · 2014 · 599 citations

, , +16

1–5 of 405

Authors

2K

  1. HT
    Heng Tao Shen

    University of Electronic Science and Technology of China, China

    10 publications · 298 citations

    10

    h-index

  2. XX
    Xing Xu

    University of Electronic Science and Technology of China, China

    10 publications · 279 citations

    10

    h-index

  3. CG
    Cathal Gurrin

    Dublin City University, Ireland

    7 publications · 243 citations

    7

    h-index

  4. YP
    Yuxin Peng

    Peking University, China

    7 publications · 504 citations

    7

    h-index

  5. LN
    Liqiang Nie

    Shandong University, China

    7 publications · 561 citations

    7

    h-index

1–5 of 2K

Institutions

420

  1. University of Electronic Science and Technology of China

    Chengdu, China

    15 h-index

    59 publications

    1.8K citations

  2. National University of Singapore

    Singapore, Singapore

    14 h-index

    33 publications

    3K citations

  3. Chinese Academy of Sciences

    Beijing, China

    13 h-index

    44 publications

    1.4K citations

  4. Peking University

    Beijing, China

    12 h-index

    28 publications

    2.3K citations

  5. Peng Cheng Laboratory

    Shenzhen, China

    11 h-index

    15 publications

    537 citations

  6. University of Chinese Academy of Sciences

    Beijing, China

    10 h-index

    18 publications

    737 citations

  7. Tsinghua University

    Beijing, China

    10 h-index

    24 publications

    2.2K citations

  8. Nanyang Technological University

    Singapore, Singapore

    9 h-index

    20 publications

    826 citations

1–8 of 420

Venues

  1. arXiv (Cornell University)

    Repository · 31 publications · 3.5K citations

    20

    h-index

  2. IEEE Transactions on Multimedia

    17 publications · 985 citations

    16

    h-index

  3. 15

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 13 publications · 1.2K citations

    13

    h-index

  5. 10

    h-index

1–5