ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic.
Yoad TewelYoav ShalevIdan SchwartzLior WolfPublished in: CVPR (2022)
Keyphrases
- input image
- low level
- image data
- multiscale
- image classification
- auto annotation
- image content
- text generation
- single image
- image features
- image analysis
- edge detection
- visual cues
- image retrieval
- visual appearance
- visual concepts
- image representation
- visual similarity
- high level semantics
- similarity measure
- semantic space
- visual perception
- web images
- spatial information
- image segmentation
- visual information
- visual data
- natural language generation
- high resolution
- artificial intelligence
- image regions
- visually similar
- visual effects
- semantic information
- visual attributes
- keypoints
- segmentation method
- data mining
- object detection
- expert systems
- object recognition
- high level
- machine learning