Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing.
Ling YangZhilong ZhangZhaochen YuJingwei LiuMinkai XuStefano ErmonBin CuiPublished in: ICLR (2024)
Keyphrases
- cross modal
- diffusion models
- multi modal
- multimedia retrieval
- text retrieval
- diffusion model
- perceptual information
- visual data
- visual similarity
- information diffusion
- visual recognition
- multimedia databases
- image retrieval
- text mining
- keywords
- social networks
- information retrieval
- web images
- influence maximization
- visual information
- text documents
- semantic information
- similarity search
- natural images
- viral marketing
- feature extraction