Aligning Linguistic Words and Visual Semantic Units for Image Captioning.
Longteng GuoJing LiuJinhui TangJiangwei LiWei LuoHanqing LuPublished in: ACM Multimedia (2019)
Keyphrases
- auto annotation
- image features
- semantic labels
- image data
- image retrieval
- image content
- low level
- visually similar
- image classification
- visual concepts
- visual similarity
- image analysis
- visual perception
- single image
- semantic meaning
- input image
- natural language
- visual features
- image representation
- visual cues
- semantic categories
- image regions
- low level visual features
- linguistic information
- multiscale
- linguistic analysis
- high level semantics
- visual data
- semantic concepts
- image collections
- high level
- natural language text
- visual appearance
- lexical semantics
- semantically related
- image segmentation
- high resolution
- image database
- natural language processing
- test images
- similarity measure
- visual effects
- keywords
- semantic space
- natural images
- semantic gap
- linguistic knowledge
- semantically meaningful
- web images