Modeling visual and word-conditional semantic attention for image captioning.
Chunlei WuYiwei WeiXiaoliang ChuFei SuLeiquan WangPublished in: Signal Process. Image Commun. (2018)
Keyphrases
- image features
- low level
- input image
- single image
- multiscale
- image classification
- image data
- image segmentation
- visually similar
- visual concepts
- image analysis
- visual data
- web images
- high level
- visual similarity
- image collections
- semantic similarity
- image content
- visual perception
- spatial information
- image representation
- co occurrence
- image retrieval
- visual appearance
- semantic space
- semantic categories
- image processing
- high level semantics
- visual information
- keypoints
- feature points
- high resolution
- natural language
- test images
- selective attention
- visual features
- visual attributes