Geometry Attention Transformer with Position-aware LSTMs for Image Captioning.
Chi WangYulin ShenLuping JiPublished in: CoRR (2021)
Keyphrases
- input image
- image content
- multiscale
- image analysis
- single image
- image data
- image features
- relative position
- image segmentation
- image retrieval
- image representation
- image classification
- keypoints
- image collections
- image pixels
- coordinate frame
- low level
- similarity measure
- template matching
- segmentation algorithm
- edge detection
- image matching
- lighting conditions
- position and orientation
- hough transform
- spatial information
- neural network
- feature points
- shape from shading
- image quality
- vision system
- geometric constraints
- image database
- light field rendering