Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment.
Junyang WangYi ZhangMing YanJi ZhangJitao SangPublished in: CoRR (2022)
Keyphrases
- image data
- single image
- image content
- image features
- image segmentation
- multiscale
- image representation
- visual perception
- similarity measure
- image retrieval
- template matching
- low level
- input image
- feature points
- computer vision
- coordinate transformation
- edge detection
- low level image processing
- image alignment
- high resolution
- keypoints
- image classification
- real time
- feature extraction
- image pixels
- image analysis
- segmentation algorithm
- d objects
- low dimensional
- hough transform
- multiresolution
- space time
- language learning
- image collections
- object categories
- pixel values
- programming language
- image synthesis
- super resolution