stonemo / oneavm

Official Codebase of "A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition" (ICML 2023)

A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition

We will release our code soon!

OneAVM is a novel framework that can unify audio-visual joint learning for localization, separation, and recognition.

A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition
Shentong Mo, Pedro Morgado
ICML 2023.

Citation

If you find this repository useful, please cite our paper:

@inproceedings{mo2023oneavm,
  title={A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition},
  author={Mo, Shentong and Morgado, Pedro},
  booktitle={Proceedings of the 40th International Conference on Machine Learning},
  year={2023}
}

oneavm's Issues

May I ask when you will open source, your work is very inspiring