Improving Compositional Text-to-image Generation with Large Vision-Language Models.
Song WenGuian FangRenrui ZhangPeng GaoHao DongDimitris MetaxasPublished in: CoRR (2023)
Keyphrases
- language model
- image generation
- information retrieval
- language modeling
- document level
- document retrieval
- n gram
- probabilistic model
- text retrieval
- language modelling
- high resolution
- query expansion
- retrieval model
- digital imaging
- test collection
- computer vision
- smoothing methods
- vision system
- statistical language models
- language models for information retrieval
- image processing
- keywords
- text documents
- video sequences
- lidar data
- image segmentation