Performance and Cost Balancing in Vision Transformer-Based Image Captioning.
Yan LyuYong LiuQiangfu ZhaoPublished in: ASSE (2023)
Keyphrases
- image features
- single image
- image analysis
- image data
- multiscale
- image retrieval
- template matching
- image classification
- image representation
- visual perception
- input image
- low level
- image content
- low level image processing
- segmentation method
- low level vision
- computer vision
- energy function
- vision system
- image regions
- test images
- region of interest
- high resolution
- image synthesis
- image segmentation
- hough transform
- spatial information
- edge detection
- image collections
- image pixels
- similarity measure
- feature extraction