The code of the paper SCAE: Structural Contrastive Auto-encoder for Incomplete Multi-view Representation Learning
This repository builds upon the work of TPAMI2022-DCP. We extend our gratitude to all the authors of this work. The datasets can be found here.
To ensure smooth execution, please install the following dependencies:
pytorch>=1.2.0numpy>=1.19.1scikit-learn>=0.23.2munkres>=1.1.4PyGCL>=0.1.0
To run the multi-view clustering script, use:
python run_clustering_multiview.pyTo run the supervised multi-view script, use:
python run_supervised_multiview.pyTo run the human action recognition tasks, use:
python run_HAR.pyIf you find our work useful, please cite the following articles:
@article{liscae,
title={SCAE: Structural Contrastive Auto-encoder for Incomplete Multi-view Representation Learning},
author={Li, Mengran and Zhang, Ronghui and Zhang, Yong and Piao, Xinglin and Zhao, Shiyu and Yin, Baocai},
journal={ACM Transactions on Multimedia Computing, Communications and Applications},
year={2024},
doi={10.1145/3672078}
}
@article{lin2022dual,
title={Dual contrastive prediction for incomplete multi-view representation learning},
author={Lin, Yijie and Gou, Yuanbiao and Liu, Xiaotian and Bai, Jinfeng and Lv, Jiancheng and Peng, Xi},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume={45},
number={4},
pages={4447--4461},
year={2022},
publisher={IEEE}
}