├── assets
    └── framework.png
└── README.md


/assets/framework.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/stoneMo/OneAVM/HEAD/assets/framework.png


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition
 2 | 
 3 | We will release our code soon! 
 4 | 
 5 | OneAVM is a novel framework that can unify audio-visual joint learning for localization, separation, and recognition.
 6 | 
 7 | [**A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition**](https://arxiv.org/abs/2305.19458)
 8 | <br>Shentong Mo, Pedro Morgado<br>
 9 | ICML 2023.
10 | 
11 | <div align="center">
12 |   <img width="100%" alt="OneAVM Illustration" src="assets/framework.png">
13 | </div>
14 | 
15 | 
16 | ## Citation
17 | 
18 | If you find this repository useful, please cite our paper:
19 | ```
20 | @inproceedings{mo2023oneavm,
21 |   title={A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition},
22 |   author={Mo, Shentong and Morgado, Pedro},
23 |   booktitle={Proceedings of the 40th International Conference on Machine Learning},
24 |   year={2023}
25 | }
26 | ```


--------------------------------------------------------------------------------