Exploiting Pseudo Image Captions for Multimodal Summarization.
Chaoya JiangRui XieWei YeJinan SunShikun ZhangPublished in: ACL (Findings) (2023)
Keyphrases
- image classification
- input image
- image analysis
- image data
- single image
- image content
- image features
- image retrieval
- multi modal
- template matching
- image segmentation
- feature points
- image representation
- low level
- high resolution
- edge detection
- image collections
- region of interest
- visual features
- spatial information
- hough transform
- segmentation method
- multiscale
- computer vision
- lighting conditions
- image set
- visual content
- image pixels
- multimodal image registration