UPainting: Unified Text-to-Image Diffusion Generation with Cross-modal Guidance.
Wei LiXue XuXinyan XiaoJiachen LiuHu YangGuohao LiZhanpeng WangZhifan FengQiaoqiao SheYajuan LyuHua WuPublished in: CoRR (2022)
Keyphrases
- cross modal
- image features
- image data
- image classification
- image retrieval
- multiscale
- test images
- information retrieval
- visual data
- low level
- web images
- multi modal
- image representation
- image collections
- image content
- spatial relationships
- image segmentation
- text retrieval
- image set
- spatial information
- image regions
- text mining
- object recognition
- feature extraction
- perceptual information