MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration

Thomas Hayes, Songyang Zhang, Xi Yin, Guan Pang, Sasha Sheng, Harry Yang, Songwei Ge, Qiyuan Hu, Devi Parikh

BibTeX
@inproceedings{hayes2022mugen,
  author = {Thomas Hayes and Songyang Zhang and Xi Yin and Guan Pang and Sasha Sheng and Harry Yang and Songwei Ge and Qiyuan Hu and Devi Parikh},
  title = {{MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration}},
  booktitle = {European Conference on Computer Vision},
  year = {2022},
  doi = {10.1007/978-3-031-20074-8\_25},
}
Figure