Aligning Linguistic Words and Visual Semantic Units for Image Captioning.
Longteng GuoJing LiuJinhui TangJiangwei LiWei LuoHanqing LuPublished in: CoRR (2019)
Keyphrases
- auto annotation
- visual perception
- image data
- image analysis
- multiscale
- semantic labels
- linguistic analysis
- semantic categories
- visual appearance
- single image
- image regions
- visual cues
- low level
- visual concepts
- image classification
- visual similarity
- edge detection
- semantic meaning
- segmentation method
- high level
- visual data
- linguistic information
- visually similar
- lexical semantics
- image segmentation
- natural language
- image retrieval
- image features
- input image
- test images
- image representation
- visual attributes
- high resolution
- natural language processing
- spatial relations
- semantic information
- visual patterns
- semantic similarity
- natural language text
- image content
- web images
- semantic space
- semantic relationships
- part of speech
- low level features
- syntactic structures
- visual effects
- word sense disambiguation
- image sequences
- arabic text
- image collections