Beyond Text-to-Image: Multimodal Prompts to Explore Generative AI.
Vivian LiuPublished in: CHI Extended Abstracts (2023)
Keyphrases
- image content
- multiscale
- image data
- input image
- single image
- artificial intelligence
- image features
- template matching
- web images
- high resolution
- segmentation method
- image representation
- image analysis
- image retrieval
- image regions
- edge detection
- image classification
- test images
- image collections
- multi modal
- pixel values
- image pixels
- keywords
- bounding box
- text information
- region of interest
- spatial information
- generative model
- feature points
- text mining
- color images
- similarity measure
- image processing