LISA: Localized Image Stylization with Audio

A novel framework for audio-guided local image stylization, named LISA. Audio-visual sound source localizer provides a delicate localization map by leveraging the CLIP embedding space in a weakly supervised manner.

Data and Resources

Cite this as

Seung Hyun Lee, Chanyoung Kim, Wonmin Byeon, Sang Ho Yoon, Jinkyu Kim, Sangpil Kim (2024). Dataset: LISA: Localized Image Stylization with Audio. https://doi.org/10.57702/sbydgh3h

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2211.11381
Author Seung Hyun Lee
More Authors
Chanyoung Kim
Wonmin Byeon
Sang Ho Yoon
Jinkyu Kim
Sangpil Kim