The Use of Object Labels and Spatial Prepositions as Keywords in a Web-Retrieval-Based Image Caption Generation System.
Brandon BirminghamAdrian MuscatPublished in: VL@EACL (2017)
Keyphrases
- spatial relationships
- bounding box
- spatial relations
- web retrieval
- spatial information
- image features
- keywords
- image retrieval
- image content
- image classification
- image representation
- image regions
- caption text
- search engine
- quad trees
- visual features
- user queries
- text classification
- low level
- digital libraries
- training data