Wang et al. "V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I14.29475
Markdown
[Wang et al. "V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/wang2024aaai-v/) doi:10.1609/AAAI.V38I14.29475
BibTeX
@inproceedings{wang2024aaai-v,
title = {{V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models}},
author = {Wang, Heng and Ma, Jianbo and Pascual, Santiago and Cartwright, Richard and Cai, Weidong},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {15492-15501},
doi = {10.1609/AAAI.V38I14.29475},
url = {https://mlanthology.org/aaai/2024/wang2024aaai-v/}
}