Position-guided transformer for image captioning.
Juntao HuYou YangLu YaoYongzhi AnLongyue PanPublished in: Image Vis. Comput. (2022)
Keyphrases
- single image
- input image
- image features
- image classification
- image data
- image analysis
- image segmentation
- image content
- segmentation method
- image retrieval
- grey level
- position and orientation
- similarity measure
- multiscale
- low level
- vector field
- image regions
- energy function
- high resolution
- feature points
- template matching
- test images
- image matching
- expert systems
- hough transform
- d objects
- neural network
- optical flow
- keypoints
- region of interest
- image collections
- image pixels
- gray level
- color images
- camera positions
- coordinate frame