Bridging the Gap between Vision and Language Domains for Improved Image Captioning.
Fenglin LiuXian WuShen GeXiaoyu ZhangWei FanYuexian ZouPublished in: ACM Multimedia (2020)
Keyphrases
- image data
- image features
- image classification
- image content
- single image
- test images
- multiscale
- input image
- image pixels
- visual perception
- template matching
- programming language
- computer vision
- image regions
- image retrieval
- image noise
- image collections
- image segmentation
- spatial information
- real time
- image representation
- vision system
- image synthesis
- edge detection
- high resolution
- feature points
- low level image processing
- low level vision
- grey level
- color vision
- segmentation algorithm
- image structure
- vector field
- keypoints
- medical images
- image analysis
- similarity measure
- real world