Scaling Up Vision-Language Pretraining for Image Captioning.
Xiaowei HuZhe GanJianfeng WangZhengyuan YangZicheng LiuYumao LuLijuan WangPublished in: CVPR (2022)
Keyphrases
- multiscale
- image data
- image features
- image content
- image analysis
- single image
- image classification
- low level image processing
- input image
- image segmentation
- image pixels
- language learning
- template matching
- computer vision
- hough transform
- low level
- high resolution
- image retrieval
- edge detection
- image noise
- grey level
- image processing
- programming language
- feature points
- image representation
- image regions
- natural language
- test images
- real time
- low level vision
- color vision
- image structure
- segmentation method
- medical images
- image database
- image registration
- high level