Better Cross-Modal Retrieval

This repo contains official implementations of our series of work in Cross-modal Retrieval:

• [EMNLP 2023] Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks

• [EMNLP Findings 2023] InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution

• [EMNLP Findings 2023] Video-Text Retrieval by Supervised Sparse Multi-Grained Learning

Reference

If you find this code useful or use the extracted similarity matrices, please consider citing:

@InProceedings{Wang01_2023_EMNLP,
    author    = {Yimu Wang, Xiangru Jian, Bo Xue},
    title     = {{Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks}},
    booktitle = {EMNLP},
    year      = {2023},
}

@InProceedings{Jian_2023_EMNLP,
    author    = {Xiangru Jian, Yimu Wang},
    title     = {{InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution}},
    booktitle = {Findings of EMNLP},
    year      = {2023},
}

@misc{wang2023videotext,
      title={Video-Text Retrieval by Supervised Multi-Space Multi-Grained Alignment}, 
      author={Yimu Wang and Peng Shi},
      year={2023},
      eprint={2302.09473},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}