ViTA: Visual-Linguistic Translation by Aligning Object Tags.
Kshitij GuptaDevansh GautamRadhika MamidiPublished in: CoRR (2021)
Keyphrases
- visual objects
- visual information
- visual features
- visual input
- low level
- d objects
- natural language processing
- spatial relations
- object model
- contextual cues
- visual properties
- object orientation
- visual appearance
- metadata
- object models
- web resources
- social bookmarking
- natural language
- high level
- web pages
- category specific
- search engine