Fine-grained Cross-modal Fusion based Refinement for Text-to-Image Synthesis.
Haoran SunYang WangHaipeng LiuBiao QianPublished in: CoRR (2023)
Keyphrases
- fine grained
- image synthesis
- cross modal
- coarse grained
- multi modal
- computer graphics
- multimedia retrieval
- text retrieval
- access control
- information retrieval
- visual recognition
- text mining
- image retrieval
- specular reflection
- virtual environment
- text documents
- keywords
- text categorization
- face recognition
- image classification
- multimedia databases
- visual data
- multimedia
- high dimensional
- object recognition
- visual similarity