Image Alone Are Not Enough: A General Semantic-Augmented Transformer-Based Framework for Image Captioning.
Jiawei LiuXin LinLiang HePublished in: IJCNN (2023)
Keyphrases
- image data
- input image
- image features
- image analysis
- edge detection
- multiscale
- image retrieval
- special case
- image classification
- high resolution
- template matching
- segmentation method
- bayesian framework
- image regions
- single image
- image content
- image representation
- image segmentation
- low level
- image pixels
- computer vision
- image database
- image collections
- keypoints
- vector field
- region of interest
- image structure
- medical images
- energy function
- feature extraction
- image processing