Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning.
Yujia XieLuowei ZhouXiyang DaiLu YuanNguyen BachCe LiuMichael ZengPublished in: CoRR (2022)
Keyphrases
- visual perception
- image data
- image features
- low level
- input image
- multiscale
- image analysis
- single image
- visual appearance
- image segmentation
- high resolution
- image classification
- image representation
- image pixels
- visual cues
- image collections
- image retrieval
- real time
- human visual
- edge detection
- natural language
- web images
- region of interest
- template matching
- visual processing
- visual similarity
- visual effects
- computer vision
- test images
- image content
- spatial information
- image processing
- visual data
- image structure
- human vision
- visual patterns
- segmentation method
- visual features
- spatial layout
- vision system
- low level image processing