A Vision Enhanced Framework for Indonesian Multimodal Abstractive Text-Image Summarization.
Yutao SongNankai LinLingbao LiShengyi JiangPublished in: CSCWD (2024)
Keyphrases
- image data
- input image
- single image
- image classification
- image features
- image collections
- low level
- image content
- feature points
- computer vision
- visual perception
- bayesian framework
- image analysis
- image segmentation
- test images
- image retrieval
- vision system
- multi modal
- segmentation method
- region of interest
- keywords
- multiscale
- web images
- multiple modalities
- segmentation algorithm
- edge detection
- spatial information
- probabilistic model
- similarity measure
- text information