ACMA-GAN: Adaptive Cross-Modal Attention for Text-to-Image Generation.

Longlong Zhou Xiaojun Wu Tianyang Xu

Published in: ICIG (4) (2023)

Keyphrases

image generation
cross modal
multi modal
high resolution
multimedia retrieval
text retrieval
digital imaging
image retrieval
information retrieval
visual recognition
image processing
image sequences
image data
input image
visual data
web images
multimedia