Modular Action Concept Grounding in Semantic Video Prediction (CVPR 2022)

The official PyTorch implementation of MAC (CVPR 2022).
Project page: http://www.pair.toronto.edu/mac/.
Paper: https://arxiv.org/abs/2011.11201

For any questions regarding the codebase, please send a message at: mail.utoronto.ca

If you use this codebase or find this repository helpful then please cite our paper:

@inproceedings{yu2022modular,
  title={Modular Action Concept Grounding in Semantic Video Prediction},
  author={Yu, Wei and Chen, Wenxin and Yin, Songhenh and Easterbrook, Steve and Garg, Animesh},
  booktitle={Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2022}
}