Transferable Decoding with Visual Entities for Zero-Shot Image Captioning.
Junjie FeiTeng WangJinrui ZhangZhenyu HeChengjie WangFeng ZhengPublished in: CoRR (2023)
Keyphrases
- image analysis
- image data
- multiscale
- low level
- image features
- single image
- visual perception
- image content
- image classification
- image retrieval
- input image
- visual cues
- image representation
- high level
- image pixels
- decoding process
- visual appearance
- edge detection
- image regions
- high resolution
- image collections
- visually similar
- image segmentation
- visual data
- pixel values
- test images
- image matching
- medical image retrieval
- human observers
- human visual
- visual properties
- web image search
- visual concepts
- web images
- spatial relations
- spatial information
- feature points
- image quality
- medical images
- image database
- feature extraction