Visual Captioning at Will: Describing Images and Videos Guided by a Few Stylized Sentences.
Dingyi YangHongyu ChenXinglin HouTiezheng GeYuning JiangQin JinPublished in: CoRR (2023)
Keyphrases
- visual data
- web images
- image data
- image database
- input image
- object recognition
- visual appearance
- image retrieval
- image analysis
- visual features
- visual environment
- visual effects
- image features
- three dimensional
- image collections
- ground truth
- visual concepts
- visual patterns
- visual information
- image set
- test images
- image registration
- segmentation method
- image classification
- visual attention
- video sequences
- natural language
- eye tracking data
- edge detection
- content based retrieval
- spatial information
- medical images
- visual analysis
- video images
- photo collections
- visually similar
- image annotation
- image processing
- low level descriptors