VGDIFFZERO: Text-To-Image Diffusion Models Can Be Zero-Shot Visual Grounders.

Xuyang Liu Siteng Huang Yachen Kang Honggang Chen Donglin Wang

Published in: ICASSP (2024)

Keyphrases

web images
image data
input image
multiscale
image retrieval
image analysis
image segmentation
information retrieval
high resolution
diffusion models
image features
edge detection
moving objects
social media
visual information