Towards local visual modeling for image captioning.
Yiwei MaJiayi JiXiaoshuai SunYiyi ZhouRongrong JiPublished in: Pattern Recognit. (2023)
Keyphrases
- visual perception
- multiscale
- image features
- image data
- input image
- image content
- edge detection
- image analysis
- low level
- visual cues
- spatial relations
- image representation
- single image
- visually similar
- visual appearance
- segmentation method
- template matching
- spatial information
- image regions
- image classification
- high resolution
- image retrieval
- visual attributes
- hough transform
- feature extraction
- visual information
- test images
- visual features
- feature points
- image collections
- image pixels
- super resolution
- auto annotation