Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation

The complete documents for reproduction are provided in Download or 国内下载源.

The detailed settings are included in 'train.py', and 'python train.py' can easily run the RML algorithm.

If you find it useful for your work, please consider to cite:

@InProceedings{Xu_2025_ICCV,
    author    = {Xu, Jie and Zhao, Na and Niu, Gang and Sugiyama, Masashi and Zhu, Xiaofeng},
    title     = {Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2025},
    pages     = {4232-4241}
}