Exploiting Pseudo Image Captions for Multimodal Summarization.
Chaoya JiangRui XieWei YeJinan SunShikun ZhangPublished in: CoRR (2023)
Keyphrases
- image data
- image features
- input image
- single image
- image retrieval
- image classification
- image pixels
- template matching
- image analysis
- image matching
- pixel values
- image structure
- image regions
- segmentation method
- image segmentation
- low level
- high resolution
- image representation
- spatial information
- image content
- test images
- multiscale
- hough transform
- image collections
- segmentation algorithm
- multi modal
- image database
- similarity measure