ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation.
Yuxiang WeiYabo ZhangZhilong JiJinfeng BaiLei ZhangWangmeng ZuoPublished in: CoRR (2023)
Keyphrases
- image generation
- visual concepts
- keywords
- visual content
- high resolution
- video content
- image content
- learning tasks
- text documents
- semantic concepts
- image collections
- digital imaging
- positive examples
- text mining
- object categories
- dimensionality reduction
- image annotation
- generative model
- video retrieval
- metadata
- visual information
- semantic gap
- three dimensional
- low dimensional
- image processing