Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning.
Yujia XieLuowei ZhouXiyang DaiLu YuanNguyen BachCe LiuMichael ZengPublished in: NeurIPS (2022)
Keyphrases
- visual perception
- image data
- single image
- low level
- multiscale
- input image
- image content
- image features
- visual appearance
- template matching
- visual cues
- image analysis
- image classification
- image collections
- high resolution
- image pixels
- medical image retrieval
- image representation
- image retrieval
- human visual
- visual concepts
- human observers
- visual processing
- visually similar
- visual input
- artificial intelligence
- region of interest
- visual information
- image set
- keypoints
- visual features
- computer vision
- image processing
- natural language
- binocular vision
- low level image processing
- real time
- visual field
- edge detection
- visual similarity
- vision system
- image quality
- visual patterns
- human vision
- web images