VGDiffZero: Text-to-Image Diffusion Models Can Be Zero-Shot Visual Grounders

VGDiffZero is a zero-shot visual grounding framework that leverages pre-trained text-to-image diffusion models' vision-language alignment abilities.

Data and Resources

Cite this as

Xuyang Liu, Siteng Huang, Yachen Kang, Honggang Chen, Donglin Wang (2024). Dataset: VGDiffZero: Text-to-Image Diffusion Models Can Be Zero-Shot Visual Grounders. https://doi.org/10.57702/5c7ldj53

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.2309.01141
Author Xuyang Liu
More Authors
Siteng Huang
Yachen Kang
Honggang Chen
Donglin Wang
Homepage https://github.com/xuyang-liu16/VGDiffZero