/MIAN

Code for paper "Modality-Invariant Asymmetric Networks for Cross-Modal Hashing"

Primary LanguagePython

Modality-Invariant Asymmetric Networks for Cross-Modal Hashing -- PyTorch Implementation

Modality-Invariant Asymmetric Networks (MIAN)

The details can be found in the TKDE 2022 paper.

Implementation platform:

  • python 3.7
  • pytorch 1.9.0
  • See requirements.txt for other package requirements.

Datasets

We use the following datasets.

  • MIRFlickr-25k
  • MSCOCO
  • NUSWIDE

Training

The command for training is

  • python3 Main.py

If you find the code is useful, please cite the following references:

Z. Zhang, H. Luo, L. Zhu, G. Lu, H. T. Shen, Modality-Invariant Asymmetric Networks for Cross-Modal Hashing, IEEE Transactions on Knowledge and Data Engineering (TKDE), DOI: 10.1109/TKDE.2022.3144352, 2022.

@article{zhang2022modality,
  title={Modality-Invariant Asymmetric Networks for Cross-Modal Hashing},
  author={Zhang, Zheng and Luo, Haoyang and Zhu, Lei and Lu, Guangming and Shen, Heng Tao},
  journal={IEEE Transactions on Knowledge and Data Engineering},
  year={2022},
  publisher={IEEE}
}