Home

Awesome

Code of paper 'Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining'

paper link: https://arxiv.org/abs/2107.14572

Product1M

The train dataset file is too large to upload here, please use the Google link below.

The dataset can be downloaded via: https://drive.google.com/drive/folders/1wIuRMo11y4VC0pI0cs0mF4X60Sw5kZQO?usp=sharing

In the .txt file, each sample contains two image urls which refer to the same image file. So you can use any one of them to download images.

If you have any questions, please do not hesitate to contact me via email {zhanxlin@mail2.sysu.edu.cn}

Capture

Code of CAPTURE can be found in 'CAPTURE' dir

Citation

@InProceedings{Zhan_2021_ICCV,
    author    = {Zhan, Xunlin and Wu, Yangxin and Dong, Xiao and Wei, Yunchao and Lu, Minlong and Zhang, Yichi and Xu, Hang and Liang, Xiaodan},
    title     = {Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-Modal Pretraining},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {11782-11791}
}