Unified Vision-Language Pre-Training for Image Captioning and VQA.
Luowei ZhouHamid PalangiLei ZhangHoudong HuJason J. CorsoJianfeng GaoPublished in: AAAI (2020)
Keyphrases
- single image
- multiscale
- image content
- image features
- image segmentation
- computer vision
- low level image processing
- visual perception
- image analysis
- test images
- image regions
- image classification
- image data
- image retrieval
- image representation
- image database
- input image
- high resolution
- segmentation algorithm
- image collections
- video database
- edge detection
- programming language
- spatial information
- low level
- object recognition
- geometric distortions
- natural language