V2L

The official code for V2L: Leveraging Vision and Vision-language Models into Large-scale Product Retrieval (CVPR 2022 Challenge Rank 1 Solution)

About the challenge

FGVC9: eBay eProduct Visual Search Challenge 2022

About the performance

About the access

If you are interested in the code, please write a request email (with your purpose and your personal information) to [email protected].

Acknowledgement

The codebase is based on our former work 1st Place Solution of the Facebook AI Image Similarity Challenge and 3rd Place Solution of the Facebook AI Image Similarity Challenge.

Citation

@misc{wang2022v2l,
    title={V$^2$L: Leveraging Vision and Vision-language Models into Large-scale Product Retrieval},
    author={Wenhao Wang and Yifan Sun and Zongxin Yang and Yi Yang},
    year={2022},
    eprint={2207.12994},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

@article{wang2021bag,
  title={Bag of tricks and a strong baseline for image copy detection},
  author={Wang, Wenhao and Zhang, Weipu and Sun, Yifan and Yang, Yi},
  journal={arXiv preprint arXiv:2111.08004},
  year={2021}
}

@article{wang2021d,
  title={D\^{} 2LV: A Data-Driven and Local-Verification Approach for Image Copy Detection},
  author={Wang, Wenhao and Sun, Yifan and Zhang, Weipu and Yang, Yi},
  journal={arXiv preprint arXiv:2111.07090},
  year={2021}
}