Transferable Decoding with Visual Entities for Zero-Shot Image Captioning.
Junjie FeiTeng WangJinrui ZhangZhenyu HeChengjie WangFeng ZhengPublished in: ICCV (2023)
Keyphrases
- image data
- single image
- input image
- image content
- visual perception
- image features
- low level
- multiscale
- visual cues
- image collections
- template matching
- image retrieval
- visual appearance
- image representation
- image analysis
- edge detection
- visually similar
- image segmentation
- image pixels
- decoding process
- visual data
- spatial information
- image regions
- image classification
- similarity measure
- image sequences
- test images
- spatial relations
- hough transform
- pixel values
- image quality
- object recognition
- visual effects
- computer vision