Multimodal Procedural Planning via Dual Text-Image Prompting.
Yujie LuPan LuZhiyu ChenWanrong ZhuXin Eric WangWilliam Yang WangPublished in: CoRR (2023)
Keyphrases
- input image
- template matching
- image pixels
- image features
- image data
- image content
- single image
- edge detection
- low level
- image analysis
- web images
- image retrieval
- multiscale
- natural images
- text information
- segmentation method
- image classification
- information retrieval
- similarity measure
- segmentation algorithm
- image matching
- test images
- image representation
- text mining
- region of interest
- information extraction
- high resolution
- textual information
- image processing